Base-size accurate tier: per-row results · onenlp docs

The gate is the paired comparison with spaCy 3.8.18 trained on the same data: 144 rows, 117 ahead, 14 within the paired interval, 13 behind (listed there and in the README's known gaps).

Information: published research systems (Stanza, UDPipe 2, Trankit) train a separate, larger model per treebank and are not a gate for this package. Three views of the same rows (no averaging over languages or metrics):

Best published system per row: 1314 comparisons, 1205 misses, 109 within the interval or ahead.
Stanza 1.5.1 pretrained/charlm, no transformer: 650 comparisons, 534 misses, 116 within the interval or ahead.
All published system comparisons: 2678 comparisons, 2346 misses, 332 within the interval or ahead.

Intervals: 95% bootstrap, 1,000 resamples, seed 20261106. The published reference passes when it is no higher than our upper bound; these are not paired intervals against the reference. Gold and raw input are never crossed. A missing reference is not a pass. The reference UD version and test-split change flag accompany every comparison; changed splits are information, not a claim of equal evaluation data. Entirely absent gold columns are not scored. Before is the previous nine-language model, where available.

Language / treebank	Input	Metric	Before [95% CI]	Current [95% CI]	Best published view	Stanza-only view
af: UD_Afrikaans-AfriBooms	gold	AllTags	not measured	84.60 [83.80, 85.35]	95.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
af: UD_Afrikaans-AfriBooms	gold	CLAS	not measured	71.68 [70.24, 73.17]	not published	not published
af: UD_Afrikaans-AfriBooms	gold	LAS	not measured	77.91 [76.68, 79.12]	87.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
af: UD_Afrikaans-AfriBooms	gold	Lemmas	not measured	96.86 [96.44, 97.24]	98.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
af: UD_Afrikaans-AfriBooms	gold	MLAS	not measured	61.10 [59.33, 62.75]	79.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
af: UD_Afrikaans-AfriBooms	gold	UAS	not measured	83.28 [82.11, 84.33]	90.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
af: UD_Afrikaans-AfriBooms	gold	UFeats	not measured	94.08 [93.53, 94.58]	98.32 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
af: UD_Afrikaans-AfriBooms	gold	UPOS	not measured	95.81 [95.37, 96.24]	98.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
af: UD_Afrikaans-AfriBooms	gold	XPOS	not measured	86.44 [85.68, 87.14]	95.94 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
af: UD_Afrikaans-AfriBooms	raw	AllTags	not measured	82.91 [82.17, 83.62]	96.54 (Trankit large, UD 2.5; test changed) — MISS	95.66 (Stanza 1.5.1, UD 2.12; test same size) — MISS
af: UD_Afrikaans-AfriBooms	raw	CLAS	not measured	75.53 [73.96, 77.02]	85.30 (Trankit large, UD 2.5; test changed) — MISS	80.10 (Stanza 1.5.1, UD 2.12; test same size) — MISS
af: UD_Afrikaans-AfriBooms	raw	LAS	not measured	79.24 [77.98, 80.45]	89.35 (Trankit large, UD 2.5; test changed) — MISS	86.14 (Stanza 1.5.1, UD 2.12; test same size) — MISS
af: UD_Afrikaans-AfriBooms	raw	Lemmas	not measured	93.98 [93.46, 94.48]	98.29 (Stanza 1.5.1, UD 2.12; test same size) — MISS	98.29 (Stanza 1.5.1, UD 2.12; test same size) — MISS
af: UD_Afrikaans-AfriBooms	raw	MLAS	not measured	65.29 [63.55, 66.93]	82.64 (Trankit large, UD 2.5; test changed) — MISS	76.71 (Stanza 1.5.1, UD 2.12; test same size) — MISS
af: UD_Afrikaans-AfriBooms	raw	Sentences	not measured	95.74 [93.63, 97.51]	100.00 (Trankit large, UD 2.5; test changed) — MISS	99.65 (Stanza 1.5.1, UD 2.12; test same size) — MISS
af: UD_Afrikaans-AfriBooms	raw	Tokens	not measured	96.77 [96.31, 97.18]	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS
af: UD_Afrikaans-AfriBooms	raw	UAS	not measured	83.39 [82.21, 84.57]	91.61 (Trankit large, UD 2.5; test changed) — MISS	89.54 (Stanza 1.5.1, UD 2.12; test same size) — MISS
af: UD_Afrikaans-AfriBooms	raw	UFeats	not measured	92.19 [91.62, 92.77]	98.68 (Trankit large, UD 2.5; test changed) — MISS	98.41 (Stanza 1.5.1, UD 2.12; test same size) — MISS
af: UD_Afrikaans-AfriBooms	raw	UPOS	not measured	93.68 [93.13, 94.18]	98.87 (Trankit large, UD 2.5; test changed) — MISS	98.60 (Stanza 1.5.1, UD 2.12; test same size) — MISS
af: UD_Afrikaans-AfriBooms	raw	Words	not measured	96.77 [96.31, 97.18]	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS
af: UD_Afrikaans-AfriBooms	raw	XPOS	not measured	84.46 [83.73, 85.13]	96.63 (Trankit large, UD 2.5; test changed) — MISS	95.77 (Stanza 1.5.1, UD 2.12; test same size) — MISS
as: UD_Assamese-AiW	gold	CLAS	not measured	54.29 [43.90, 64.79]	not published	not published
as: UD_Assamese-AiW	gold	LAS	not measured	58.82 [47.62, 69.88]	not published	not published
as: UD_Assamese-AiW	gold	Lemmas	not measured	67.06 [54.55, 79.52]	not published	not published
as: UD_Assamese-AiW	gold	MLAS	not measured	24.29 [17.65, 32.12]	not published	not published
as: UD_Assamese-AiW	gold	UAS	not measured	76.47 [61.25, 88.10]	not published	not published
as: UD_Assamese-AiW	gold	UFeats	not measured	47.06 [37.65, 58.54]	not published	not published
as: UD_Assamese-AiW	gold	UPOS	not measured	75.29 [66.27, 82.14]	not published	not published
as: UD_Assamese-AiW	raw	CLAS	not measured	56.74 [42.96, 71.76]	not published	not published
as: UD_Assamese-AiW	raw	LAS	not measured	60.00 [47.73, 73.49]	not published	not published
as: UD_Assamese-AiW	raw	Lemmas	not measured	65.88 [54.55, 76.67]	not published	not published
as: UD_Assamese-AiW	raw	MLAS	not measured	21.28 [10.61, 33.59]	not published	not published
as: UD_Assamese-AiW	raw	Sentences	not measured	100.00 [100.00, 100.00]	not published	not published
as: UD_Assamese-AiW	raw	Tokens	not measured	100.00 [100.00, 100.00]	not published	not published
as: UD_Assamese-AiW	raw	UAS	not measured	78.82 [68.60, 87.80]	not published	not published
as: UD_Assamese-AiW	raw	UFeats	not measured	45.88 [39.77, 54.02]	not published	not published
as: UD_Assamese-AiW	raw	UPOS	not measured	64.71 [56.32, 74.03]	not published	not published
as: UD_Assamese-AiW	raw	Words	not measured	100.00 [100.00, 100.00]	not published	not published
bor: UD_Bororo-BDT	gold	AllTags	not measured	51.11 [50.40, 51.90]	84.62 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	gold	CLAS	not measured	42.27 [41.09, 43.51]	not published	not published
bor: UD_Bororo-BDT	gold	LAS	not measured	46.49 [45.35, 47.72]	72.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	gold	Lemmas	not measured	83.28 [82.59, 83.87]	91.56 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	gold	MLAS	not measured	19.95 [19.11, 20.80]	59.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	gold	UAS	not measured	56.91 [55.72, 58.22]	79.11 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	gold	UFeats	not measured	66.97 [66.22, 67.69]	89.82 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	gold	UPOS	not measured	71.89 [71.13, 72.67]	91.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	gold	XPOS	not measured	71.09 [70.35, 71.87]	90.74 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	raw	AllTags	not measured	51.81 [51.09, 52.61]	84.54 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	raw	CLAS	not measured	47.37 [46.01, 48.70]	not published	not published
bor: UD_Bororo-BDT	raw	LAS	not measured	51.41 [50.20, 52.63]	72.57 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	raw	Lemmas	not measured	84.21 [83.57, 84.80]	91.56 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	raw	MLAS	not measured	23.75 [22.80, 24.70]	59.79 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	raw	Sentences	not measured	79.78 [78.05, 81.40]	97.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	raw	Tokens	not measured	99.79 [99.69, 99.88]	not published	not published
bor: UD_Bororo-BDT	raw	UAS	not measured	61.94 [60.73, 63.13]	78.80 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	raw	UFeats	not measured	66.81 [66.07, 67.53]	89.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	raw	UPOS	not measured	73.84 [73.10, 74.60]	91.68 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	raw	Words	not measured	99.79 [99.69, 99.88]	99.99 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bor: UD_Bororo-BDT	raw	XPOS	not measured	72.25 [71.52, 73.02]	90.68 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
bxr: UD_Buryat-BDT	gold	AllTags	not measured	8.16 [7.52, 8.78]	not published	not published
bxr: UD_Buryat-BDT	gold	CLAS	not measured	20.67 [19.71, 21.64]	not published	not published
bxr: UD_Buryat-BDT	gold	LAS	not measured	25.01 [23.98, 25.97]	not published	not published
bxr: UD_Buryat-BDT	gold	Lemmas	not measured	57.00 [56.07, 58.05]	not published	not published
bxr: UD_Buryat-BDT	gold	MLAS	not measured	1.15 [0.92, 1.39]	not published	not published
bxr: UD_Buryat-BDT	gold	UAS	not measured	47.48 [46.02, 48.87]	not published	not published
bxr: UD_Buryat-BDT	gold	UFeats	not measured	39.30 [38.32, 40.29]	not published	not published
bxr: UD_Buryat-BDT	gold	UPOS	not measured	20.69 [19.98, 21.43]	not published	not published
bxr: UD_Buryat-BDT	gold	XPOS	not measured	99.99 [99.97, 100.00]	not published	not published
bxr: UD_Buryat-BDT	raw	AllTags	not measured	8.25 [7.61, 8.89]	67.97 (Stanza 1.5.1, UD 2.12; test changed) — MISS	67.97 (Stanza 1.5.1, UD 2.12; test changed) — MISS
bxr: UD_Buryat-BDT	raw	CLAS	not measured	22.31 [21.34, 23.32]	31.58 (Stanza 1.5.1, UD 2.12; test changed) — MISS	31.58 (Stanza 1.5.1, UD 2.12; test changed) — MISS
bxr: UD_Buryat-BDT	raw	LAS	not measured	26.11 [25.14, 27.17]	40.52 (Stanza 1.5.1, UD 2.12; test changed) — MISS	40.52 (Stanza 1.5.1, UD 2.12; test changed) — MISS
bxr: UD_Buryat-BDT	raw	Lemmas	not measured	55.90 [54.95, 56.93]	77.78 (Stanza 1.5.1, UD 2.12; test changed) — MISS	77.78 (Stanza 1.5.1, UD 2.12; test changed) — MISS
bxr: UD_Buryat-BDT	raw	MLAS	not measured	1.39 [1.11, 1.67]	24.88 (Stanza 1.5.1, UD 2.12; test changed) — MISS	24.88 (Stanza 1.5.1, UD 2.12; test changed) — MISS
bxr: UD_Buryat-BDT	raw	Sentences	not measured	18.61 [16.41, 20.73]	100.00 (Stanza 1.5.1, UD 2.12; test changed) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test changed) — MISS
bxr: UD_Buryat-BDT	raw	Tokens	not measured	99.54 [99.31, 99.74]	100.00 (Stanza 1.5.1, UD 2.12; test changed) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test changed) — MISS
bxr: UD_Buryat-BDT	raw	UAS	not measured	48.91 [47.69, 50.08]	56.21 (Stanza 1.5.1, UD 2.12; test changed) — MISS	56.21 (Stanza 1.5.1, UD 2.12; test changed) — MISS
bxr: UD_Buryat-BDT	raw	UFeats	not measured	37.35 [36.44, 38.25]	74.51 (Stanza 1.5.1, UD 2.12; test changed) — MISS	74.51 (Stanza 1.5.1, UD 2.12; test changed) — MISS
bxr: UD_Buryat-BDT	raw	UPOS	not measured	23.55 [22.73, 24.34]	75.16 (Stanza 1.5.1, UD 2.12; test changed) — MISS	75.16 (Stanza 1.5.1, UD 2.12; test changed) — MISS
bxr: UD_Buryat-BDT	raw	Words	not measured	99.54 [99.31, 99.74]	100.00 (Stanza 1.5.1, UD 2.12; test changed) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test changed) — MISS
bxr: UD_Buryat-BDT	raw	XPOS	not measured	99.53 [99.28, 99.73]	100.00 (Stanza 1.5.1, UD 2.12; test changed) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	gold	AllTags	not measured	75.95 [75.36, 76.56]	96.98 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ca: UD_Catalan-AnCora	gold	CLAS	not measured	78.17 [77.49, 78.84]	not published	not published
ca: UD_Catalan-AnCora	gold	LAS	not measured	83.64 [83.10, 84.16]	93.46 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ca: UD_Catalan-AnCora	gold	Lemmas	not measured	98.06 [97.92, 98.19]	99.49 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ca: UD_Catalan-AnCora	gold	MLAS	not measured	64.60 [63.86, 65.35]	88.08 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ca: UD_Catalan-AnCora	gold	UAS	not measured	87.28 [86.79, 87.77]	94.98 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ca: UD_Catalan-AnCora	gold	UFeats	not measured	93.07 [92.81, 93.32]	98.75 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ca: UD_Catalan-AnCora	gold	UPOS	not measured	95.95 [95.74, 96.14]	99.15 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ca: UD_Catalan-AnCora	gold	XPOS	not measured	77.80 [77.23, 78.38]	97.27 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ca: UD_Catalan-AnCora	raw	AllTags	not measured	69.68 [69.10, 70.32]	98.24 (Trankit large, UD 2.5; test changed) — MISS	95.67 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	raw	CLAS	not measured	71.60 [70.83, 72.41]	91.41 (Trankit large, UD 2.5; test changed) — MISS	87.24 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	raw	LAS	not measured	73.13 [72.51, 73.80]	93.83 (Trankit large, UD 2.5; test changed) — MISS	91.66 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	raw	Lemmas	not measured	87.71 [87.37, 88.04]	99.43 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.06 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	raw	MLAS	not measured	56.53 [55.72, 57.32]	89.31 (Trankit large, UD 2.5; test changed) — MISS	84.72 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	raw	Sentences	not measured	89.47 [88.25, 90.72]	100.00 (Trankit base, UD 2.5; test changed) — MISS	99.57 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	raw	Tokens	not measured	93.67 [93.42, 93.91]	99.97 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.97 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	raw	UAS	not measured	75.62 [75.01, 76.27]	95.15 (Trankit large, UD 2.5; test changed) — MISS	93.55 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	raw	UFeats	not measured	83.14 [82.75, 83.53]	98.67 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	98.27 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	raw	UPOS	not measured	86.15 [85.78, 86.50]	99.11 (Trankit large, UD 2.5; test changed) — MISS	98.70 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	raw	Words	not measured	89.32 [88.99, 89.64]	99.95 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.95 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ca: UD_Catalan-AnCora	raw	XPOS	not measured	71.10 [70.53, 71.72]	99.07 (Trankit large, UD 2.5; test changed) — MISS	95.93 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ckb: UD_Central_Kurdish-Mukri	gold	CLAS	not measured	23.08 [14.91, 31.43]	not published	not published
ckb: UD_Central_Kurdish-Mukri	gold	LAS	not measured	34.43 [26.12, 42.96]	not published	not published
ckb: UD_Central_Kurdish-Mukri	gold	Lemmas	not measured	64.75 [57.98, 70.87]	not published	not published
ckb: UD_Central_Kurdish-Mukri	gold	MLAS	not measured	8.97 [2.72, 15.69]	not published	not published
ckb: UD_Central_Kurdish-Mukri	gold	UAS	not measured	47.54 [35.07, 59.84]	not published	not published
ckb: UD_Central_Kurdish-Mukri	gold	UFeats	not measured	54.92 [46.40, 62.77]	not published	not published
ckb: UD_Central_Kurdish-Mukri	gold	UPOS	not measured	54.10 [47.46, 60.17]	not published	not published
ckb: UD_Central_Kurdish-Mukri	raw	CLAS	not measured	19.05 [9.30, 29.46]	not published	not published
ckb: UD_Central_Kurdish-Mukri	raw	LAS	not measured	27.83 [18.10, 37.44]	not published	not published
ckb: UD_Central_Kurdish-Mukri	raw	Lemmas	not measured	55.65 [49.54, 61.80]	not published	not published
ckb: UD_Central_Kurdish-Mukri	raw	MLAS	not measured	5.44 [0.00, 11.76]	not published	not published
ckb: UD_Central_Kurdish-Mukri	raw	Sentences	not measured	93.33 [82.61, 100.00]	not published	not published
ckb: UD_Central_Kurdish-Mukri	raw	Tokens	not measured	100.00 [100.00, 100.00]	not published	not published
ckb: UD_Central_Kurdish-Mukri	raw	UAS	not measured	33.91 [21.70, 46.28]	not published	not published
ckb: UD_Central_Kurdish-Mukri	raw	UFeats	not measured	49.57 [42.62, 56.56]	not published	not published
ckb: UD_Central_Kurdish-Mukri	raw	UPOS	not measured	51.30 [43.88, 58.72]	not published	not published
ckb: UD_Central_Kurdish-Mukri	raw	Words	not measured	81.74 [75.00, 88.11]	not published	not published
cop: UD_Coptic-Scriptorium	gold	AllTags	not measured	62.73 [61.51, 63.94]	96.10 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
cop: UD_Coptic-Scriptorium	gold	CLAS	not measured	38.27 [36.78, 40.01]	not published	not published
cop: UD_Coptic-Scriptorium	gold	LAS	not measured	51.38 [50.04, 52.70]	88.27 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
cop: UD_Coptic-Scriptorium	gold	Lemmas	not measured	88.04 [87.22, 88.88]	97.67 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
cop: UD_Coptic-Scriptorium	gold	MLAS	not measured	20.89 [19.66, 22.19]	78.68 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
cop: UD_Coptic-Scriptorium	gold	UAS	not measured	62.23 [60.95, 63.61]	91.07 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
cop: UD_Coptic-Scriptorium	gold	UFeats	not measured	72.24 [71.18, 73.33]	97.94 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
cop: UD_Coptic-Scriptorium	gold	UPOS	not measured	76.21 [75.18, 77.17]	97.42 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
cop: UD_Coptic-Scriptorium	gold	XPOS	not measured	73.58 [72.49, 74.68]	97.16 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
cop: UD_Coptic-Scriptorium	raw	AllTags	not measured	15.13 [14.46, 15.83]	84.77 (Stanza 1.5.1, UD 2.12; test changed) — MISS	84.77 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cop: UD_Coptic-Scriptorium	raw	CLAS	not measured	0.61 [0.37, 0.89]	56.39 (Stanza 1.5.1, UD 2.12; test changed) — MISS	56.39 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cop: UD_Coptic-Scriptorium	raw	LAS	not measured	0.80 [0.55, 1.10]	64.43 (Stanza 1.5.1, UD 2.12; test changed) — MISS	64.43 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cop: UD_Coptic-Scriptorium	raw	Lemmas	not measured	22.46 [21.49, 23.51]	85.95 (Stanza 1.5.1, UD 2.12; test changed) — MISS	85.95 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cop: UD_Coptic-Scriptorium	raw	MLAS	not measured	0.24 [0.11, 0.40]	53.08 (Stanza 1.5.1, UD 2.12; test changed) — MISS	53.08 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cop: UD_Coptic-Scriptorium	raw	Sentences	not measured	5.15 [2.78, 8.19]	34.09 (Stanza 1.5.1, UD 2.12; test changed) — MISS	34.09 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cop: UD_Coptic-Scriptorium	raw	Tokens	not measured	99.49 [98.85, 99.94]	100.00 (Stanza 1.5.1, UD 2.12; test changed) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cop: UD_Coptic-Scriptorium	raw	UAS	not measured	0.97 [0.68, 1.32]	66.37 (Stanza 1.5.1, UD 2.12; test changed) — MISS	66.37 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cop: UD_Coptic-Scriptorium	raw	UFeats	not measured	16.99 [16.30, 17.69]	86.37 (Stanza 1.5.1, UD 2.12; test changed) — MISS	86.37 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cop: UD_Coptic-Scriptorium	raw	UPOS	not measured	16.78 [16.00, 17.54]	85.77 (Stanza 1.5.1, UD 2.12; test changed) — MISS	85.77 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cop: UD_Coptic-Scriptorium	raw	Words	not measured	23.13 [22.10, 24.19]	88.63 (Stanza 1.5.1, UD 2.12; test changed) — MISS	88.63 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cop: UD_Coptic-Scriptorium	raw	XPOS	not measured	16.82 [16.08, 17.59]	85.69 (Stanza 1.5.1, UD 2.12; test changed) — MISS	85.69 (Stanza 1.5.1, UD 2.12; test changed) — MISS
cs: UD_Czech-CAC	gold	AllTags	not measured	68.03 [67.08, 68.96]	97.42 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cs: UD_Czech-CAC	gold	CLAS	not measured	80.85 [79.61, 82.10]	not published	not published
cs: UD_Czech-CAC	gold	LAS	not measured	83.93 [82.92, 84.99]	94.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cs: UD_Czech-CAC	gold	Lemmas	not measured	94.33 [93.83, 94.84]	99.28 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cs: UD_Czech-CAC	gold	MLAS	not measured	48.87 [47.38, 50.51]	90.46 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cs: UD_Czech-CAC	gold	UAS	not measured	87.40 [86.41, 88.27]	96.25 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cs: UD_Czech-CAC	gold	UFeats	not measured	73.92 [73.03, 74.80]	97.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cs: UD_Czech-CAC	gold	UPOS	not measured	95.08 [94.62, 95.50]	99.59 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cs: UD_Czech-CAC	gold	XPOS	not measured	76.79 [75.91, 77.66]	98.20 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cs: UD_Czech-CAC	raw	AllTags	not measured	70.84 [70.01, 71.68]	97.65 (Trankit large, UD 2.5; test same size) — MISS	92.92 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cs: UD_Czech-CAC	raw	CLAS	not measured	86.79 [85.63, 87.85]	93.06 (Trankit large, UD 2.5; test same size) — MISS	86.78 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
cs: UD_Czech-CAC	raw	LAS	not measured	88.56 [87.59, 89.47]	94.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	88.71 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
cs: UD_Czech-CAC	raw	Lemmas	not measured	95.06 [94.57, 95.50]	99.27 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	97.46 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cs: UD_Czech-CAC	raw	MLAS	not measured	55.33 [53.88, 56.80]	90.44 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	80.27 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cs: UD_Czech-CAC	raw	Sentences	not measured	97.60 [96.39, 98.72]	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cs: UD_Czech-CAC	raw	Tokens	not measured	99.92 [99.82, 99.98]	99.99 (Trankit large, UD 2.5; test same size) — MISS	99.82 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
cs: UD_Czech-CAC	raw	UAS	not measured	91.21 [90.28, 92.08]	96.25 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	91.09 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
cs: UD_Czech-CAC	raw	UFeats	not measured	75.72 [74.89, 76.56]	98.01 (Trankit large, UD 2.5; test same size) — MISS	93.64 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cs: UD_Czech-CAC	raw	UPOS	not measured	95.77 [95.32, 96.18]	99.64 (Trankit large, UD 2.5; test same size) — MISS	98.52 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cs: UD_Czech-CAC	raw	Words	not measured	99.67 [99.53, 99.78]	99.99 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.57 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
cs: UD_Czech-CAC	raw	XPOS	not measured	79.17 [78.37, 79.96]	98.20 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.59 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	gold	AllTags	not measured	74.20 [73.55, 74.85]	88.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cy: UD_Welsh-CCG	gold	CLAS	not measured	70.34 [69.27, 71.39]	not published	not published
cy: UD_Welsh-CCG	gold	LAS	not measured	75.92 [75.04, 76.75]	82.61 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cy: UD_Welsh-CCG	gold	Lemmas	not measured	91.15 [90.67, 91.63]	95.32 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cy: UD_Welsh-CCG	gold	MLAS	not measured	44.09 [42.90, 45.16]	65.14 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cy: UD_Welsh-CCG	gold	UAS	not measured	82.71 [81.92, 83.51]	88.45 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cy: UD_Welsh-CCG	gold	UFeats	not measured	79.27 [78.69, 79.90]	90.30 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cy: UD_Welsh-CCG	gold	UPOS	not measured	91.91 [91.45, 92.36]	95.89 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cy: UD_Welsh-CCG	gold	XPOS	not measured	91.03 [90.54, 91.45]	94.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
cy: UD_Welsh-CCG	raw	AllTags	not measured	67.37 [66.61, 68.13]	87.83 (Stanza 1.5.1, UD 2.12; test same size) — MISS	87.83 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	raw	CLAS	not measured	62.93 [61.67, 64.17]	74.85 (Stanza 1.5.1, UD 2.12; test same size) — MISS	74.85 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	raw	LAS	not measured	64.89 [63.74, 65.95]	81.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	80.25 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	raw	Lemmas	not measured	81.89 [81.22, 82.52]	94.89 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.85 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	raw	MLAS	not measured	37.17 [36.08, 38.25]	64.32 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	62.81 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	raw	Sentences	not measured	81.61 [79.19, 83.90]	97.79 (Stanza 1.5.1, UD 2.12; test same size) — MISS	97.79 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	raw	Tokens	not measured	92.22 [91.66, 92.72]	99.90 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.90 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	raw	UAS	not measured	70.58 [69.41, 71.73]	87.52 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	86.32 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	raw	UFeats	not measured	70.70 [69.97, 71.41]	90.11 (Stanza 1.5.1, UD 2.12; test same size) — MISS	90.11 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	raw	UPOS	not measured	84.08 [83.38, 84.71]	95.86 (Stanza 1.5.1, UD 2.12; test same size) — MISS	95.86 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	raw	Words	not measured	89.93 [89.38, 90.50]	99.68 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.68 (Stanza 1.5.1, UD 2.12; test same size) — MISS
cy: UD_Welsh-CCG	raw	XPOS	not measured	83.40 [82.70, 84.08]	94.60 (Stanza 1.5.1, UD 2.12; test same size) — MISS	94.60 (Stanza 1.5.1, UD 2.12; test same size) — MISS
da: UD_Danish-DDT	gold	AllTags	not measured	1.00 [0.83, 1.19]	96.88 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
da: UD_Danish-DDT	gold	CLAS	not measured	70.27 [68.75, 71.83]	not published	not published
da: UD_Danish-DDT	gold	LAS	not measured	74.84 [73.49, 76.18]	87.87 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
da: UD_Danish-DDT	gold	Lemmas	not measured	94.41 [93.87, 94.92]	97.65 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
da: UD_Danish-DDT	gold	MLAS	not measured	55.74 [54.13, 57.42]	80.77 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
da: UD_Danish-DDT	gold	UAS	not measured	78.94 [77.63, 80.25]	89.84 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
da: UD_Danish-DDT	gold	UFeats	not measured	90.63 [89.97, 91.21]	97.63 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
da: UD_Danish-DDT	gold	UPOS	not measured	94.66 [94.09, 95.18]	98.20 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
da: UD_Danish-DDT	gold	XPOS	not measured	1.00 [0.83, 1.19]	100.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
da: UD_Danish-DDT	raw	AllTags	not measured	0.99 [0.82, 1.18]	97.87 (Trankit large, UD 2.5; test same size) — MISS	97.14 (Stanza 1.5.1, UD 2.12; test same size) — MISS
da: UD_Danish-DDT	raw	CLAS	not measured	77.30 [75.79, 78.87]	88.81 (Trankit large, UD 2.5; test same size) — MISS	83.80 (Stanza 1.5.1, UD 2.12; test same size) — MISS
da: UD_Danish-DDT	raw	LAS	not measured	80.60 [79.35, 81.96]	90.33 (Trankit large, UD 2.5; test same size) — MISS	86.61 (Stanza 1.5.1, UD 2.12; test same size) — MISS
da: UD_Danish-DDT	raw	Lemmas	not measured	93.97 [93.43, 94.52]	97.88 (Stanza 1.5.1, UD 2.12; test same size) — MISS	97.88 (Stanza 1.5.1, UD 2.12; test same size) — MISS
da: UD_Danish-DDT	raw	MLAS	not measured	65.32 [63.63, 67.11]	85.66 (Trankit large, UD 2.5; test same size) — MISS	80.06 (Stanza 1.5.1, UD 2.12; test same size) — MISS
da: UD_Danish-DDT	raw	Sentences	not measured	93.90 [91.83, 95.75]	95.46 (Trankit large, UD 2.5; test same size) — within or ahead	91.81 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
da: UD_Danish-DDT	raw	Tokens	not measured	98.69 [98.37, 99.02]	99.97 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.97 (Stanza 1.5.1, UD 2.12; test same size) — MISS
da: UD_Danish-DDT	raw	UAS	not measured	83.84 [82.62, 85.19]	91.75 (Trankit large, UD 2.5; test same size) — MISS	88.61 (Stanza 1.5.1, UD 2.12; test same size) — MISS
da: UD_Danish-DDT	raw	UFeats	not measured	91.29 [90.67, 91.88]	98.33 (Trankit large, UD 2.5; test same size) — MISS	97.87 (Stanza 1.5.1, UD 2.12; test same size) — MISS
da: UD_Danish-DDT	raw	UPOS	not measured	94.32 [93.75, 94.85]	98.71 (Trankit large, UD 2.5; test same size) — MISS	98.30 (Stanza 1.5.1, UD 2.12; test same size) — MISS
da: UD_Danish-DDT	raw	Words	not measured	98.69 [98.37, 99.02]	99.97 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.97 (Stanza 1.5.1, UD 2.12; test same size) — MISS
da: UD_Danish-DDT	raw	XPOS	not measured	0.99 [0.82, 1.18]	99.97 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.97 (Stanza 1.5.1, UD 2.12; test same size) — MISS
de: UD_German-GSD	gold	AllTags	83.34 [82.57, 84.04]	83.09 [82.34, 83.75]	89.21 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
de: UD_German-GSD	gold	CLAS	not measured	78.67 [77.54, 79.74]	not published	not published
de: UD_German-GSD	gold	LAS	83.32 [82.43, 84.17]	83.49 [82.59, 84.31]	86.16 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
de: UD_German-GSD	gold	Lemmas	96.25 [95.95, 96.53]	96.64 [96.37, 96.92]	97.37 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
de: UD_German-GSD	gold	MLAS	not measured	59.58 [58.38, 60.86]	69.30 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
de: UD_German-GSD	gold	UAS	87.01 [86.18, 87.75]	87.09 [86.26, 87.84]	89.24 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
de: UD_German-GSD	gold	UFeats	86.81 [86.11, 87.44]	86.58 [85.91, 87.19]	91.53 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
de: UD_German-GSD	gold	UPOS	96.16 [95.83, 96.49]	95.78 [95.43, 96.12]	97.11 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
de: UD_German-GSD	gold	XPOS	96.07 [95.71, 96.43]	95.84 [95.48, 96.19]	97.93 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
de: UD_German-GSD	raw	AllTags	81.04 [80.35, 81.70]	81.69 [80.99, 82.33]	88.82 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	87.19 (Stanza 1.5.1, UD 2.12; test changed) — MISS
de: UD_German-GSD	raw	CLAS	not measured	81.12 [80.13, 82.07]	81.49 (Trankit large, UD 2.5; test changed) — within or ahead	77.08 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
de: UD_German-GSD	raw	LAS	81.17 [80.27, 82.00]	82.38 [81.55, 83.18]	85.20 (Trankit large, UD 2.5; test changed) — MISS	81.80 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
de: UD_German-GSD	raw	Lemmas	93.36 [92.90, 93.78]	94.07 [93.64, 94.48]	97.23 (Stanza 1.5.1, UD 2.12; test changed) — MISS	97.23 (Stanza 1.5.1, UD 2.12; test changed) — MISS
de: UD_German-GSD	raw	MLAS	not measured	60.36 [59.24, 61.44]	67.63 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	62.81 (Stanza 1.5.1, UD 2.12; test changed) — MISS
de: UD_German-GSD	raw	Sentences	88.70 [86.70, 90.74]	88.65 [86.73, 90.58]	92.72 (Trankit base, UD 2.5; test changed) — MISS	83.84 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
de: UD_German-GSD	raw	Tokens	97.40 [97.09, 97.69]	97.40 [97.09, 97.69]	99.75 (Trankit base, UD 2.5; test changed) — MISS	99.62 (Stanza 1.5.1, UD 2.12; test changed) — MISS
de: UD_German-GSD	raw	UAS	84.71 [83.86, 85.52]	85.50 [84.64, 86.25]	89.01 (Trankit large, UD 2.5; test changed) — MISS	85.80 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
de: UD_German-GSD	raw	UFeats	84.39 [83.77, 85.03]	85.16 [84.51, 85.74]	91.68 (Trankit large, UD 2.5; test changed) — MISS	89.78 (Stanza 1.5.1, UD 2.12; test changed) — MISS
de: UD_German-GSD	raw	UPOS	93.27 [92.79, 93.69]	93.33 [92.87, 93.75]	96.87 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	95.61 (Stanza 1.5.1, UD 2.12; test changed) — MISS
de: UD_German-GSD	raw	Words	97.06 [96.70, 97.39]	97.06 [96.70, 97.39]	99.79 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.60 (Stanza 1.5.1, UD 2.12; test changed) — MISS
de: UD_German-GSD	raw	XPOS	93.38 [92.91, 93.83]	93.35 [92.91, 93.79]	97.71 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	97.36 (Stanza 1.5.1, UD 2.12; test changed) — MISS
egy: UD_Egyptian-PC	gold	AllTags	not measured	0.00 [0.00, 0.00]	not published	not published
egy: UD_Egyptian-PC	gold	CLAS	not measured	37.45 [36.31, 38.59]	not published	not published
egy: UD_Egyptian-PC	gold	LAS	not measured	42.41 [41.30, 43.51]	not published	not published
egy: UD_Egyptian-PC	gold	Lemmas	not measured	84.54 [83.73, 85.28]	not published	not published
egy: UD_Egyptian-PC	gold	MLAS	not measured	19.05 [18.22, 19.98]	not published	not published
egy: UD_Egyptian-PC	gold	UAS	not measured	57.76 [56.65, 58.80]	not published	not published
egy: UD_Egyptian-PC	gold	UFeats	not measured	52.85 [51.87, 53.87]	not published	not published
egy: UD_Egyptian-PC	gold	UPOS	not measured	73.69 [72.75, 74.56]	not published	not published
egy: UD_Egyptian-PC	gold	XPOS	not measured	0.00 [0.00, 0.00]	not published	not published
egy: UD_Egyptian-PC	raw	AllTags	not measured	0.00 [0.00, 0.00]	not published	not published
egy: UD_Egyptian-PC	raw	CLAS	not measured	9.42 [8.82, 10.07]	not published	not published
egy: UD_Egyptian-PC	raw	LAS	not measured	12.52 [11.81, 13.22]	not published	not published
egy: UD_Egyptian-PC	raw	Lemmas	not measured	38.59 [37.53, 39.58]	not published	not published
egy: UD_Egyptian-PC	raw	MLAS	not measured	5.15 [4.72, 5.61]	not published	not published
egy: UD_Egyptian-PC	raw	Sentences	not measured	3.26 [2.26, 4.34]	not published	not published
egy: UD_Egyptian-PC	raw	Tokens	not measured	46.31 [45.19, 47.45]	not published	not published
egy: UD_Egyptian-PC	raw	UAS	not measured	16.51 [15.72, 17.36]	not published	not published
egy: UD_Egyptian-PC	raw	UFeats	not measured	25.94 [25.02, 26.83]	not published	not published
egy: UD_Egyptian-PC	raw	UPOS	not measured	32.00 [31.01, 32.89]	not published	not published
egy: UD_Egyptian-PC	raw	Words	not measured	45.07 [43.98, 46.14]	not published	not published
egy: UD_Egyptian-PC	raw	XPOS	not measured	0.00 [0.00, 0.00]	not published	not published
el: UD_Greek-GUD	gold	CLAS	not measured	81.01 [79.90, 82.11]	not published	not published
el: UD_Greek-GUD	gold	LAS	not measured	82.87 [81.91, 83.75]	90.79 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
el: UD_Greek-GUD	gold	Lemmas	not measured	90.86 [90.34, 91.41]	95.97 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
el: UD_Greek-GUD	gold	MLAS	not measured	49.27 [47.87, 50.55]	77.89 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
el: UD_Greek-GUD	gold	UAS	not measured	89.65 [88.81, 90.43]	94.05 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
el: UD_Greek-GUD	gold	UFeats	not measured	78.37 [77.65, 79.14]	94.41 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
el: UD_Greek-GUD	gold	UPOS	not measured	92.10 [91.62, 92.62]	98.13 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
el: UD_Greek-GUD	raw	CLAS	not measured	83.78 [82.69, 84.84]	80.28 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead	80.28 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
el: UD_Greek-GUD	raw	LAS	not measured	83.08 [82.11, 84.02]	90.37 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	85.33 (Stanza 1.5.1, UD 2.12; test changed) — MISS
el: UD_Greek-GUD	raw	Lemmas	not measured	87.84 [87.21, 88.52]	95.93 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	92.63 (Stanza 1.5.1, UD 2.12; test changed) — MISS
el: UD_Greek-GUD	raw	MLAS	not measured	52.10 [50.79, 53.43]	77.62 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	68.93 (Stanza 1.5.1, UD 2.12; test changed) — MISS
el: UD_Greek-GUD	raw	Sentences	not measured	92.76 [90.99, 94.36]	98.16 (Stanza 1.5.1, UD 2.12; test changed) — MISS	98.16 (Stanza 1.5.1, UD 2.12; test changed) — MISS
el: UD_Greek-GUD	raw	Tokens	not measured	99.51 [99.34, 99.69]	99.89 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.89 (Stanza 1.5.1, UD 2.12; test changed) — MISS
el: UD_Greek-GUD	raw	UAS	not measured	86.89 [85.95, 87.74]	93.61 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	89.81 (Stanza 1.5.1, UD 2.12; test changed) — MISS
el: UD_Greek-GUD	raw	UFeats	not measured	77.20 [76.41, 78.02]	94.36 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	92.50 (Stanza 1.5.1, UD 2.12; test changed) — MISS
el: UD_Greek-GUD	raw	UPOS	not measured	90.62 [90.00, 91.21]	98.08 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	96.52 (Stanza 1.5.1, UD 2.12; test changed) — MISS
el: UD_Greek-GUD	raw	Words	not measured	95.55 [95.09, 96.04]	99.94 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	99.89 (Stanza 1.5.1, UD 2.12; test changed) — MISS
en: UD_English-EWT	gold	AllTags	93.66 [93.25, 94.02]	93.47 [93.07, 93.83]	96.34 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
en: UD_English-EWT	gold	CLAS	not measured	81.48 [80.57, 82.45]	not published	not published
en: UD_English-EWT	gold	LAS	85.43 [84.61, 86.19]	85.12 [84.40, 85.87]	92.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
en: UD_English-EWT	gold	Lemmas	97.09 [96.81, 97.36]	97.26 [97.01, 97.52]	97.96 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
en: UD_English-EWT	gold	MLAS	not measured	75.10 [74.10, 76.11]	86.29 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
en: UD_English-EWT	gold	UAS	88.56 [87.81, 89.26]	88.34 [87.65, 89.01]	94.09 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
en: UD_English-EWT	gold	UFeats	96.44 [96.17, 96.69]	96.37 [96.09, 96.62]	98.13 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
en: UD_English-EWT	gold	UPOS	96.58 [96.26, 96.86]	96.49 [96.19, 96.76]	97.61 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
en: UD_English-EWT	gold	XPOS	96.02 [95.69, 96.32]	95.73 [95.40, 96.04]	97.13 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
en: UD_English-EWT	raw	AllTags	93.14 [92.69, 93.57]	93.39 [92.93, 93.80]	95.51 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.64 (Stanza 1.5.1, UD 2.12; test changed) — MISS
en: UD_English-EWT	raw	CLAS	not measured	83.38 [82.51, 84.30]	87.41 (Trankit large, UD 2.5; test changed) — MISS	84.11 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
en: UD_English-EWT	raw	LAS	85.02 [84.25, 85.77]	86.55 [85.82, 87.26]	89.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	86.77 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
en: UD_English-EWT	raw	Lemmas	96.14 [95.81, 96.48]	96.39 [96.04, 96.74]	97.25 (Trankit large, UD 2.5; test changed) — MISS	96.63 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
en: UD_English-EWT	raw	MLAS	not measured	78.46 [77.50, 79.41]	83.87 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	80.27 (Stanza 1.5.1, UD 2.12; test changed) — MISS
en: UD_English-EWT	raw	Sentences	75.28 [73.54, 77.14]	75.85 [74.20, 77.60]	90.49 (Trankit large, UD 2.5; test changed) — MISS	89.16 (Stanza 1.5.1, UD 2.12; test changed) — MISS
en: UD_English-EWT	raw	Tokens	97.13 [96.83, 97.43]	97.13 [96.83, 97.43]	99.17 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.17 (Stanza 1.5.1, UD 2.12; test changed) — MISS
en: UD_English-EWT	raw	UAS	87.32 [86.58, 88.01]	88.78 [88.07, 89.47]	91.59 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	88.90 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
en: UD_English-EWT	raw	UFeats	95.76 [95.42, 96.07]	95.94 [95.61, 96.27]	97.21 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.39 (Stanza 1.5.1, UD 2.12; test changed) — MISS
en: UD_English-EWT	raw	UPOS	95.95 [95.59, 96.29]	95.95 [95.59, 96.27]	96.75 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.20 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
en: UD_English-EWT	raw	Words	98.68 [98.45, 98.90]	98.68 [98.45, 98.90]	99.07 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	98.92 (Stanza 1.5.1, UD 2.12; test changed) — MISS
en: UD_English-EWT	raw	XPOS	95.22 [94.83, 95.58]	95.18 [94.78, 95.54]	96.47 (Trankit large, UD 2.5; test changed) — MISS	95.75 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	gold	AllTags	83.67 [83.20, 84.13]	83.21 [82.74, 83.67]	95.64 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
es: UD_Spanish-AnCora	gold	CLAS	not measured	82.53 [81.95, 83.14]	not published	not published
es: UD_Spanish-AnCora	gold	LAS	85.37 [84.89, 85.88]	86.97 [86.51, 87.42]	92.26 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
es: UD_Spanish-AnCora	gold	Lemmas	97.72 [97.58, 97.85]	98.53 [98.42, 98.64]	99.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
es: UD_Spanish-AnCora	gold	MLAS	not measured	75.87 [75.23, 76.53]	87.03 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
es: UD_Spanish-AnCora	gold	UAS	88.14 [87.68, 88.63]	89.50 [89.08, 89.94]	94.01 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
es: UD_Spanish-AnCora	gold	UFeats	96.50 [96.33, 96.66]	96.74 [96.58, 96.91]	98.79 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
es: UD_Spanish-AnCora	gold	UPOS	98.10 [97.98, 98.24]	98.00 [97.87, 98.14]	99.09 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
es: UD_Spanish-AnCora	gold	XPOS	84.88 [84.41, 85.31]	84.37 [83.90, 84.82]	96.12 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
es: UD_Spanish-AnCora	raw	AllTags	84.50 [84.05, 84.94]	84.84 [84.40, 85.29]	98.36 (Trankit large, UD 2.5; test changed) — MISS	95.65 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	raw	CLAS	not measured	86.36 [85.78, 86.89]	91.10 (Trankit large, UD 2.5; test changed) — MISS	87.80 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	raw	LAS	87.42 [86.90, 87.92]	89.70 [89.24, 90.11]	93.29 (Trankit large, UD 2.5; test changed) — MISS	91.30 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	raw	Lemmas	97.75 [97.61, 97.89]	98.58 [98.46, 98.70]	99.37 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.24 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	raw	MLAS	not measured	80.63 [79.97, 81.23]	89.23 (Trankit large, UD 2.5; test changed) — MISS	85.49 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	raw	Sentences	96.66 [95.79, 97.49]	97.05 [96.24, 97.78]	99.39 (Trankit large, UD 2.5; test changed) — MISS	98.49 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	raw	Tokens	99.84 [99.76, 99.90]	99.84 [99.76, 99.90]	99.97 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.97 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	raw	UAS	90.08 [89.60, 90.51]	91.93 [91.49, 92.31]	94.77 (Trankit large, UD 2.5; test changed) — MISS	93.09 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	raw	UFeats	96.57 [96.40, 96.73]	96.83 [96.66, 96.99]	98.85 (Trankit large, UD 2.5; test changed) — MISS	98.54 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	raw	UPOS	98.09 [97.96, 98.24]	98.20 [98.07, 98.34]	99.06 (Trankit large, UD 2.5; test changed) — MISS	98.96 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	raw	Words	99.83 [99.75, 99.89]	99.83 [99.75, 99.89]	99.96 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.96 (Stanza 1.5.1, UD 2.12; test changed) — MISS
es: UD_Spanish-AnCora	raw	XPOS	85.63 [85.17, 86.09]	85.87 [85.43, 86.33]	99.00 (Trankit large, UD 2.5; test changed) — MISS	96.10 (Stanza 1.5.1, UD 2.12; test changed) — MISS
fa: UD_Persian-Seraji	gold	AllTags	not measured	1.58 [1.38, 1.79]	97.82 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fa: UD_Persian-Seraji	gold	CLAS	not measured	61.56 [60.30, 62.91]	not published	not published
fa: UD_Persian-Seraji	gold	LAS	not measured	66.70 [65.63, 67.81]	89.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fa: UD_Persian-Seraji	gold	Lemmas	not measured	96.14 [95.87, 96.43]	98.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fa: UD_Persian-Seraji	gold	MLAS	not measured	29.39 [28.32, 30.42]	85.29 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fa: UD_Persian-Seraji	gold	UAS	not measured	73.22 [72.20, 74.32]	92.62 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fa: UD_Persian-Seraji	gold	UFeats	not measured	72.36 [71.68, 73.09]	98.27 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fa: UD_Persian-Seraji	gold	UPOS	not measured	85.15 [84.41, 85.81]	98.30 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fa: UD_Persian-Seraji	gold	XPOS	not measured	3.41 [3.09, 3.75]	98.28 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fa: UD_Persian-Seraji	raw	AllTags	not measured	4.75 [4.35, 5.14]	97.49 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	97.31 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fa: UD_Persian-Seraji	raw	CLAS	not measured	65.75 [64.46, 66.96]	86.86 (Trankit large, UD 2.5; test same size) — MISS	85.43 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fa: UD_Persian-Seraji	raw	LAS	not measured	70.39 [69.29, 71.48]	89.58 (Trankit large, UD 2.5; test same size) — MISS	87.96 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fa: UD_Persian-Seraji	raw	Lemmas	not measured	95.47 [95.12, 95.82]	98.57 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	98.18 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fa: UD_Persian-Seraji	raw	MLAS	not measured	32.32 [31.28, 33.28]	84.97 (Trankit large, UD 2.5; test same size) — MISS	83.76 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fa: UD_Persian-Seraji	raw	Sentences	not measured	90.42 [88.10, 92.57]	99.25 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.25 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fa: UD_Persian-Seraji	raw	Tokens	not measured	100.00 [100.00, 100.00]	100.00 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	100.00 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
fa: UD_Persian-Seraji	raw	UAS	not measured	76.52 [75.54, 77.59]	92.24 (Trankit large, UD 2.5; test same size) — MISS	90.98 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fa: UD_Persian-Seraji	raw	UFeats	not measured	72.04 [71.38, 72.80]	97.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	97.70 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fa: UD_Persian-Seraji	raw	UPOS	not measured	86.26 [85.61, 86.83]	97.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	97.69 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fa: UD_Persian-Seraji	raw	Words	not measured	99.08 [98.88, 99.28]	99.72 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.72 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fa: UD_Persian-Seraji	raw	XPOS	not measured	7.17 [6.71, 7.66]	97.93 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	97.63 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	gold	AllTags	not measured	59.08 [58.24, 59.90]	94.23 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fi: UD_Finnish-FTB	gold	CLAS	not measured	72.18 [71.04, 73.24]	not published	not published
fi: UD_Finnish-FTB	gold	LAS	not measured	72.93 [71.91, 73.94]	89.42 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fi: UD_Finnish-FTB	gold	Lemmas	not measured	81.17 [80.50, 81.86]	95.81 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fi: UD_Finnish-FTB	gold	MLAS	not measured	48.49 [47.40, 49.63]	82.72 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fi: UD_Finnish-FTB	gold	UAS	not measured	79.34 [78.40, 80.27]	92.38 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fi: UD_Finnish-FTB	gold	UFeats	not measured	78.17 [77.47, 78.83]	96.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fi: UD_Finnish-FTB	gold	UPOS	not measured	87.31 [86.69, 87.87]	97.05 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fi: UD_Finnish-FTB	gold	XPOS	not measured	62.13 [61.30, 62.92]	95.17 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fi: UD_Finnish-FTB	raw	AllTags	not measured	49.32 [48.47, 50.14]	96.87 (Trankit large, UD 2.5; test same size) — MISS	95.29 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	raw	CLAS	not measured	75.32 [74.16, 76.42]	93.54 (Trankit large, UD 2.5; test same size) — MISS	86.24 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	raw	LAS	not measured	77.41 [76.42, 78.35]	94.53 (Trankit large, UD 2.5; test same size) — MISS	88.63 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	raw	Lemmas	not measured	82.30 [81.70, 83.00]	97.10 (Stanza 1.5.1, UD 2.12; test same size) — MISS	97.10 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	raw	MLAS	not measured	52.18 [51.07, 53.35]	90.68 (Trankit large, UD 2.5; test same size) — MISS	82.60 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	raw	Sentences	not measured	87.32 [85.87, 88.72]	97.36 (Trankit large, UD 2.5; test same size) — MISS	90.13 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	raw	Tokens	not measured	99.59 [99.44, 99.72]	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	raw	UAS	not measured	82.60 [81.70, 83.50]	95.84 (Trankit large, UD 2.5; test same size) — MISS	90.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	raw	UFeats	not measured	79.28 [78.59, 79.94]	98.09 (Trankit large, UD 2.5; test same size) — MISS	97.12 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	raw	UPOS	not measured	87.62 [87.05, 88.17]	98.32 (Trankit large, UD 2.5; test same size) — MISS	96.88 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	raw	Words	not measured	99.36 [99.20, 99.51]	99.98 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.98 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fi: UD_Finnish-FTB	raw	XPOS	not measured	51.48 [50.63, 52.30]	97.29 (Trankit large, UD 2.5; test same size) — MISS	96.09 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fo: UD_Faroese-FarPaHC	gold	AllTags	not measured	77.78 [76.95, 78.63]	92.62 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fo: UD_Faroese-FarPaHC	gold	CLAS	not measured	66.42 [64.64, 68.31]	not published	not published
fo: UD_Faroese-FarPaHC	gold	LAS	not measured	71.92 [70.54, 73.47]	83.58 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fo: UD_Faroese-FarPaHC	gold	Lemmas	not measured	100.00 [100.00, 100.00]	100.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
fo: UD_Faroese-FarPaHC	gold	MLAS	not measured	47.80 [46.06, 49.66]	69.89 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fo: UD_Faroese-FarPaHC	gold	UAS	not measured	77.08 [75.67, 78.58]	87.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fo: UD_Faroese-FarPaHC	gold	UFeats	not measured	86.06 [85.32, 86.77]	94.59 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fo: UD_Faroese-FarPaHC	gold	UPOS	not measured	94.59 [94.09, 95.06]	97.65 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fo: UD_Faroese-FarPaHC	gold	XPOS	not measured	81.33 [80.53, 82.21]	93.15 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fo: UD_Faroese-FarPaHC	raw	AllTags	not measured	77.85 [76.98, 78.74]	92.46 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	90.86 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fo: UD_Faroese-FarPaHC	raw	CLAS	not measured	72.03 [70.17, 73.86]	72.28 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	72.28 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
fo: UD_Faroese-FarPaHC	raw	LAS	not measured	76.88 [75.50, 78.29]	82.71 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	80.07 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fo: UD_Faroese-FarPaHC	raw	Lemmas	not measured	99.39 [99.20, 99.58]	99.74 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.64 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fo: UD_Faroese-FarPaHC	raw	MLAS	not measured	53.79 [52.01, 55.62]	68.94 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	64.48 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fo: UD_Faroese-FarPaHC	raw	Sentences	not measured	91.84 [88.85, 94.59]	93.94 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	93.94 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
fo: UD_Faroese-FarPaHC	raw	Tokens	not measured	99.41 [99.21, 99.59]	99.65 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.65 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fo: UD_Faroese-FarPaHC	raw	UAS	not measured	82.00 [80.73, 83.34]	86.48 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	84.39 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fo: UD_Faroese-FarPaHC	raw	UFeats	not measured	86.72 [85.97, 87.46]	94.37 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	92.92 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fo: UD_Faroese-FarPaHC	raw	UPOS	not measured	94.17 [93.65, 94.68]	97.48 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.51 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fo: UD_Faroese-FarPaHC	raw	Words	not measured	99.39 [99.20, 99.58]	99.74 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.64 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fo: UD_Faroese-FarPaHC	raw	XPOS	not measured	81.38 [80.53, 82.24]	92.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	91.56 (Stanza 1.5.1, UD 2.12; test same size) — MISS
fr: UD_French-GSD	gold	CLAS	not measured	82.47 [81.26, 83.85]	not published	not published
fr: UD_French-GSD	gold	LAS	86.55 [85.57, 87.49]	86.89 [85.93, 87.88]	93.11 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fr: UD_French-GSD	gold	Lemmas	97.56 [97.23, 97.88]	98.03 [97.72, 98.31]	98.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fr: UD_French-GSD	gold	MLAS	not measured	75.00 [73.45, 76.63]	86.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fr: UD_French-GSD	gold	UAS	89.36 [88.49, 90.23]	89.52 [88.61, 90.43]	94.99 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fr: UD_French-GSD	gold	UFeats	96.24 [95.75, 96.67]	96.06 [95.58, 96.49]	98.30 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fr: UD_French-GSD	gold	UPOS	97.21 [96.82, 97.58]	96.99 [96.60, 97.39]	98.55 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
fr: UD_French-GSD	raw	CLAS	not measured	86.65 [85.41, 87.83]	90.17 (Trankit large, UD 2.5; test changed) — MISS	87.44 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
fr: UD_French-GSD	raw	LAS	88.07 [87.07, 89.05]	89.78 [88.84, 90.63]	93.37 (Trankit large, UD 2.5; test changed) — MISS	91.28 (Stanza 1.5.1, UD 2.12; test changed) — MISS
fr: UD_French-GSD	raw	Lemmas	97.42 [97.09, 97.77]	97.96 [97.64, 98.25]	98.20 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead	98.20 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
fr: UD_French-GSD	raw	MLAS	not measured	80.57 [79.06, 81.91]	86.35 (Trankit large, UD 2.5; test changed) — MISS	84.45 (Stanza 1.5.1, UD 2.12; test changed) — MISS
fr: UD_French-GSD	raw	Sentences	92.40 [89.74, 94.66]	92.65 [90.07, 94.98]	98.80 (Trankit large, UD 2.5; test changed) — MISS	95.03 (Stanza 1.5.1, UD 2.12; test changed) — MISS
fr: UD_French-GSD	raw	Tokens	99.88 [99.79, 99.96]	99.88 [99.79, 99.96]	99.77 (Trankit large, UD 2.5; test changed) — within or ahead	99.71 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
fr: UD_French-GSD	raw	UAS	90.67 [89.74, 91.58]	91.97 [91.12, 92.76]	94.97 (Trankit large, UD 2.5; test changed) — MISS	93.27 (Stanza 1.5.1, UD 2.12; test changed) — MISS
fr: UD_French-GSD	raw	UFeats	96.07 [95.59, 96.52]	96.26 [95.82, 96.68]	97.74 (Stanza 1.5.1, UD 2.12; test changed) — MISS	97.74 (Stanza 1.5.1, UD 2.12; test changed) — MISS
fr: UD_French-GSD	raw	UPOS	97.06 [96.71, 97.42]	97.10 [96.71, 97.46]	97.89 (Trankit large, UD 2.5; test changed) — MISS	97.63 (Stanza 1.5.1, UD 2.12; test changed) — MISS
fr: UD_French-GSD	raw	Words	99.48 [99.29, 99.65]	99.48 [99.29, 99.65]	99.72 (Trankit large, UD 2.5; test changed) — MISS	99.50 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
ga: UD_Irish-IDT	gold	AllTags	not measured	60.83 [59.34, 62.05]	88.57 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ga: UD_Irish-IDT	gold	CLAS	not measured	64.78 [62.68, 66.81]	not published	not published
ga: UD_Irish-IDT	gold	LAS	not measured	71.66 [69.97, 73.24]	82.20 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ga: UD_Irish-IDT	gold	Lemmas	not measured	91.11 [90.18, 91.90]	95.88 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ga: UD_Irish-IDT	gold	MLAS	not measured	32.12 [30.49, 33.73]	65.80 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ga: UD_Irish-IDT	gold	UAS	not measured	78.67 [77.14, 80.11]	87.61 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ga: UD_Irish-IDT	gold	UFeats	not measured	68.36 [67.18, 69.47]	91.43 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ga: UD_Irish-IDT	gold	UPOS	not measured	90.83 [89.85, 91.65]	96.46 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ga: UD_Irish-IDT	gold	XPOS	not measured	85.82 [84.83, 86.77]	95.27 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ga: UD_Irish-IDT	raw	AllTags	not measured	61.92 [60.46, 63.32]	88.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	86.52 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ga: UD_Irish-IDT	raw	CLAS	not measured	68.12 [65.79, 70.27]	76.34 (Stanza 1.5.1, UD 2.12; test same size) — MISS	76.34 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ga: UD_Irish-IDT	raw	LAS	not measured	73.90 [71.88, 75.71]	81.93 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	81.51 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ga: UD_Irish-IDT	raw	Lemmas	not measured	89.93 [88.98, 90.82]	95.77 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	95.32 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ga: UD_Irish-IDT	raw	MLAS	not measured	34.25 [32.40, 35.98]	65.68 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	63.38 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ga: UD_Irish-IDT	raw	Sentences	not measured	86.06 [82.70, 89.19]	98.24 (Trankit large, UD 2.5; test changed) — MISS	97.24 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ga: UD_Irish-IDT	raw	Tokens	not measured	98.09 [97.47, 98.59]	99.75 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.75 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ga: UD_Irish-IDT	raw	UAS	not measured	80.66 [78.83, 82.33]	87.31 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	86.81 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ga: UD_Irish-IDT	raw	UFeats	not measured	68.07 [66.72, 69.32]	91.32 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	89.41 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ga: UD_Irish-IDT	raw	UPOS	not measured	90.27 [89.27, 91.12]	96.35 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.01 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ga: UD_Irish-IDT	raw	Words	not measured	98.09 [97.47, 98.59]	99.88 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.75 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ga: UD_Irish-IDT	raw	XPOS	not measured	87.25 [86.27, 88.17]	95.09 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.55 (Stanza 1.5.1, UD 2.12; test same size) — MISS
gd: UD_Scottish_Gaelic-ARCOSG	gold	AllTags	not measured	65.11 [63.95, 66.15]	90.74 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gd: UD_Scottish_Gaelic-ARCOSG	gold	CLAS	not measured	64.97 [63.30, 66.43]	not published	not published
gd: UD_Scottish_Gaelic-ARCOSG	gold	LAS	not measured	71.21 [69.81, 72.39]	83.15 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gd: UD_Scottish_Gaelic-ARCOSG	gold	Lemmas	not measured	93.80 [93.19, 94.32]	97.70 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gd: UD_Scottish_Gaelic-ARCOSG	gold	MLAS	not measured	42.12 [40.61, 43.54]	72.21 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gd: UD_Scottish_Gaelic-ARCOSG	gold	UAS	not measured	78.53 [77.26, 79.68]	87.26 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gd: UD_Scottish_Gaelic-ARCOSG	gold	UFeats	not measured	77.00 [76.03, 77.94]	93.63 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gd: UD_Scottish_Gaelic-ARCOSG	gold	UPOS	not measured	90.89 [90.16, 91.57]	96.65 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gd: UD_Scottish_Gaelic-ARCOSG	gold	XPOS	not measured	70.33 [69.21, 71.31]	92.03 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gd: UD_Scottish_Gaelic-ARCOSG	raw	AllTags	not measured	54.95 [53.83, 55.93]	89.42 (Stanza 1.5.1, UD 2.12; test changed) — MISS	89.42 (Stanza 1.5.1, UD 2.12; test changed) — MISS
gd: UD_Scottish_Gaelic-ARCOSG	raw	CLAS	not measured	58.12 [56.23, 60.02]	72.86 (Stanza 1.5.1, UD 2.12; test changed) — MISS	72.86 (Stanza 1.5.1, UD 2.12; test changed) — MISS
gd: UD_Scottish_Gaelic-ARCOSG	raw	LAS	not measured	59.34 [57.76, 60.86]	77.81 (Stanza 1.5.1, UD 2.12; test changed) — MISS	77.81 (Stanza 1.5.1, UD 2.12; test changed) — MISS
gd: UD_Scottish_Gaelic-ARCOSG	raw	Lemmas	not measured	80.82 [79.94, 81.74]	95.81 (Stanza 1.5.1, UD 2.12; test changed) — MISS	95.81 (Stanza 1.5.1, UD 2.12; test changed) — MISS
gd: UD_Scottish_Gaelic-ARCOSG	raw	MLAS	not measured	34.30 [32.91, 35.65]	66.53 (Stanza 1.5.1, UD 2.12; test changed) — MISS	66.53 (Stanza 1.5.1, UD 2.12; test changed) — MISS
gd: UD_Scottish_Gaelic-ARCOSG	raw	Sentences	not measured	63.02 [59.09, 67.21]	64.54 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead	64.54 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
gd: UD_Scottish_Gaelic-ARCOSG	raw	Tokens	not measured	90.18 [89.42, 90.90]	99.65 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.65 (Stanza 1.5.1, UD 2.12; test changed) — MISS
gd: UD_Scottish_Gaelic-ARCOSG	raw	UAS	not measured	64.70 [63.06, 66.21]	82.73 (Stanza 1.5.1, UD 2.12; test changed) — MISS	82.73 (Stanza 1.5.1, UD 2.12; test changed) — MISS
gd: UD_Scottish_Gaelic-ARCOSG	raw	UFeats	not measured	65.18 [64.18, 66.18]	91.91 (Stanza 1.5.1, UD 2.12; test changed) — MISS	91.91 (Stanza 1.5.1, UD 2.12; test changed) — MISS
gd: UD_Scottish_Gaelic-ARCOSG	raw	UPOS	not measured	78.37 [77.49, 79.18]	94.70 (Trankit large, UD 2.5; test changed) — MISS	94.62 (Stanza 1.5.1, UD 2.12; test changed) — MISS
gd: UD_Scottish_Gaelic-ARCOSG	raw	Words	not measured	85.57 [84.70, 86.41]	99.42 (Trankit large, UD 2.5; test changed) — MISS	98.86 (Stanza 1.5.1, UD 2.12; test changed) — MISS
gd: UD_Scottish_Gaelic-ARCOSG	raw	XPOS	not measured	59.64 [58.48, 60.65]	90.24 (Stanza 1.5.1, UD 2.12; test changed) — MISS	90.24 (Stanza 1.5.1, UD 2.12; test changed) — MISS
gl: UD_Galician-TreeGal	gold	AllTags	not measured	81.94 [80.86, 82.94]	94.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gl: UD_Galician-TreeGal	gold	CLAS	not measured	72.40 [70.85, 74.02]	not published	not published
gl: UD_Galician-TreeGal	gold	LAS	not measured	76.69 [75.42, 77.87]	82.33 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gl: UD_Galician-TreeGal	gold	Lemmas	not measured	95.39 [94.95, 95.82]	98.56 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gl: UD_Galician-TreeGal	gold	MLAS	not measured	54.87 [53.08, 56.73]	71.66 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gl: UD_Galician-TreeGal	gold	UAS	not measured	82.48 [81.42, 83.50]	86.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gl: UD_Galician-TreeGal	gold	UFeats	not measured	87.74 [86.84, 88.54]	96.30 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gl: UD_Galician-TreeGal	gold	UPOS	not measured	91.85 [91.17, 92.52]	97.35 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gl: UD_Galician-TreeGal	gold	XPOS	not measured	85.46 [84.56, 86.30]	95.42 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
gl: UD_Galician-TreeGal	raw	AllTags	not measured	72.91 [71.91, 73.96]	94.97 (Trankit large, UD 2.5; test same size) — MISS	90.64 (Stanza 1.5.1, UD 2.12; test same size) — MISS
gl: UD_Galician-TreeGal	raw	CLAS	not measured	71.90 [70.19, 73.59]	80.31 (Trankit large, UD 2.5; test same size) — MISS	64.38 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
gl: UD_Galician-TreeGal	raw	LAS	not measured	66.34 [65.07, 67.80]	83.90 (Trankit large, UD 2.5; test same size) — MISS	71.86 (Stanza 1.5.1, UD 2.12; test same size) — MISS
gl: UD_Galician-TreeGal	raw	Lemmas	not measured	83.92 [83.08, 84.76]	97.31 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.52 (Stanza 1.5.1, UD 2.12; test same size) — MISS
gl: UD_Galician-TreeGal	raw	MLAS	not measured	49.73 [48.04, 51.36]	74.67 (Trankit large, UD 2.5; test same size) — MISS	58.14 (Stanza 1.5.1, UD 2.12; test same size) — MISS
gl: UD_Galician-TreeGal	raw	Sentences	not measured	79.95 [76.05, 83.67]	95.52 (Trankit large, UD 2.5; test same size) — MISS	88.02 (Stanza 1.5.1, UD 2.12; test same size) — MISS
gl: UD_Galician-TreeGal	raw	Tokens	not measured	99.28 [98.99, 99.53]	99.68 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.68 (Stanza 1.5.1, UD 2.12; test same size) — MISS
gl: UD_Galician-TreeGal	raw	UAS	not measured	70.24 [68.98, 71.51]	87.17 (Trankit large, UD 2.5; test same size) — MISS	77.27 (Stanza 1.5.1, UD 2.12; test same size) — MISS
gl: UD_Galician-TreeGal	raw	UFeats	not measured	78.13 [77.16, 79.07]	96.50 (Trankit large, UD 2.5; test same size) — MISS	93.11 (Stanza 1.5.1, UD 2.12; test same size) — MISS
gl: UD_Galician-TreeGal	raw	UPOS	not measured	81.47 [80.65, 82.36]	97.62 (Trankit large, UD 2.5; test same size) — MISS	93.89 (Stanza 1.5.1, UD 2.12; test same size) — MISS
gl: UD_Galician-TreeGal	raw	Words	not measured	87.31 [86.48, 88.11]	99.22 (Trankit large, UD 2.5; test same size) — MISS	98.53 (Stanza 1.5.1, UD 2.12; test same size) — MISS
gl: UD_Galician-TreeGal	raw	XPOS	not measured	75.29 [74.29, 76.34]	95.68 (Trankit large, UD 2.5; test same size) — MISS	91.51 (Stanza 1.5.1, UD 2.12; test same size) — MISS
grc: UD_Ancient_Greek-PTNK	gold	CLAS	not measured	67.13 [65.47, 68.59]	not published	not published
grc: UD_Ancient_Greek-PTNK	gold	LAS	not measured	73.13 [71.87, 74.27]	87.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	gold	Lemmas	not measured	85.61 [84.97, 86.33]	94.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	gold	MLAS	not measured	36.20 [34.57, 37.58]	70.15 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	gold	UAS	not measured	77.95 [76.78, 79.06]	92.12 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	gold	UFeats	not measured	71.83 [70.76, 72.88]	91.80 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	gold	UPOS	not measured	93.42 [92.84, 93.97]	98.55 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	raw	CLAS	not measured	70.73 [69.01, 72.43]	not published	not published
grc: UD_Ancient_Greek-PTNK	raw	LAS	not measured	75.45 [74.11, 76.71]	84.30 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	raw	Lemmas	not measured	84.76 [84.05, 85.46]	94.84 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	raw	MLAS	not measured	38.16 [36.46, 39.77]	66.93 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	raw	Sentences	not measured	46.79 [41.96, 52.07]	55.12 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	raw	Tokens	not measured	99.03 [98.78, 99.26]	not published	not published
grc: UD_Ancient_Greek-PTNK	raw	UAS	not measured	80.23 [78.90, 81.53]	88.44 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	raw	UFeats	not measured	71.42 [70.28, 72.44]	91.75 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	raw	UPOS	not measured	92.10 [91.47, 92.68]	98.57 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
grc: UD_Ancient_Greek-PTNK	raw	Words	not measured	98.96 [98.72, 99.19]	99.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
he: UD_Hebrew-IAHLTwiki	gold	AllTags	not measured	73.33 [72.42, 74.24]	91.52 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
he: UD_Hebrew-IAHLTwiki	gold	CLAS	not measured	73.52 [72.25, 74.92]	not published	not published
he: UD_Hebrew-IAHLTwiki	gold	LAS	not measured	76.97 [75.90, 78.16]	91.23 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
he: UD_Hebrew-IAHLTwiki	gold	Lemmas	not measured	94.16 [93.65, 94.62]	98.30 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
he: UD_Hebrew-IAHLTwiki	gold	MLAS	not measured	43.05 [41.54, 44.44]	75.93 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
he: UD_Hebrew-IAHLTwiki	gold	UAS	not measured	81.92 [80.92, 82.90]	93.63 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
he: UD_Hebrew-IAHLTwiki	gold	UFeats	not measured	77.07 [76.20, 77.92]	92.55 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
he: UD_Hebrew-IAHLTwiki	gold	UPOS	not measured	88.46 [87.69, 89.21]	97.12 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
he: UD_Hebrew-IAHLTwiki	gold	XPOS	not measured	90.72 [90.05, 91.35]	97.11 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
he: UD_Hebrew-IAHLTwiki	raw	AllTags	not measured	41.59 [40.42, 42.81]	86.14 (Stanza 1.5.1, UD 2.12; test changed) — MISS	86.14 (Stanza 1.5.1, UD 2.12; test changed) — MISS
he: UD_Hebrew-IAHLTwiki	raw	CLAS	not measured	27.76 [26.30, 29.28]	75.58 (Stanza 1.5.1, UD 2.12; test changed) — MISS	75.58 (Stanza 1.5.1, UD 2.12; test changed) — MISS
he: UD_Hebrew-IAHLTwiki	raw	LAS	not measured	29.34 [27.85, 30.73]	81.19 (Stanza 1.5.1, UD 2.12; test changed) — MISS	81.19 (Stanza 1.5.1, UD 2.12; test changed) — MISS
he: UD_Hebrew-IAHLTwiki	raw	Lemmas	not measured	51.58 [50.39, 52.82]	92.51 (Stanza 1.5.1, UD 2.12; test changed) — MISS	92.51 (Stanza 1.5.1, UD 2.12; test changed) — MISS
he: UD_Hebrew-IAHLTwiki	raw	MLAS	not measured	16.88 [15.80, 17.93]	64.88 (Stanza 1.5.1, UD 2.12; test changed) — MISS	64.88 (Stanza 1.5.1, UD 2.12; test changed) — MISS
he: UD_Hebrew-IAHLTwiki	raw	Sentences	not measured	42.17 [37.22, 47.57]	97.16 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.78 (Stanza 1.5.1, UD 2.12; test changed) — MISS
he: UD_Hebrew-IAHLTwiki	raw	Tokens	not measured	97.18 [96.65, 97.72]	99.64 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.64 (Stanza 1.5.1, UD 2.12; test changed) — MISS
he: UD_Hebrew-IAHLTwiki	raw	UAS	not measured	30.34 [28.78, 31.81]	83.23 (Stanza 1.5.1, UD 2.12; test changed) — MISS	83.23 (Stanza 1.5.1, UD 2.12; test changed) — MISS
he: UD_Hebrew-IAHLTwiki	raw	UFeats	not measured	42.73 [41.55, 43.94]	86.88 (Stanza 1.5.1, UD 2.12; test changed) — MISS	86.88 (Stanza 1.5.1, UD 2.12; test changed) — MISS
he: UD_Hebrew-IAHLTwiki	raw	UPOS	not measured	50.85 [49.71, 52.06]	91.69 (Stanza 1.5.1, UD 2.12; test changed) — MISS	91.69 (Stanza 1.5.1, UD 2.12; test changed) — MISS
he: UD_Hebrew-IAHLTwiki	raw	Words	not measured	54.72 [53.59, 55.98]	94.61 (Stanza 1.5.1, UD 2.12; test changed) — MISS	94.61 (Stanza 1.5.1, UD 2.12; test changed) — MISS
he: UD_Hebrew-IAHLTwiki	raw	XPOS	not measured	51.98 [50.83, 53.18]	91.69 (Stanza 1.5.1, UD 2.12; test changed) — MISS	91.69 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hr: UD_Croatian-SET	gold	AllTags	not measured	76.51 [75.83, 77.15]	95.65 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hr: UD_Croatian-SET	gold	CLAS	not measured	75.54 [74.70, 76.39]	not published	not published
hr: UD_Croatian-SET	gold	LAS	not measured	79.15 [78.36, 79.95]	89.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hr: UD_Croatian-SET	gold	Lemmas	not measured	92.20 [91.78, 92.59]	97.71 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hr: UD_Croatian-SET	gold	MLAS	not measured	54.16 [53.21, 55.13]	82.25 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hr: UD_Croatian-SET	gold	UAS	not measured	84.29 [83.63, 85.02]	92.88 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hr: UD_Croatian-SET	gold	UFeats	not measured	81.27 [80.65, 81.85]	96.44 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hr: UD_Croatian-SET	gold	UPOS	not measured	93.74 [93.41, 94.10]	98.53 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hr: UD_Croatian-SET	gold	XPOS	not measured	80.52 [79.83, 81.12]	95.90 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hr: UD_Croatian-SET	raw	AllTags	not measured	80.47 [79.88, 81.06]	95.99 (Trankit large, UD 2.5; test same size) — MISS	94.60 (Stanza 1.5.1, UD 2.12; test same size) — MISS
hr: UD_Croatian-SET	raw	CLAS	not measured	83.78 [83.02, 84.46]	87.77 (Trankit large, UD 2.5; test same size) — MISS	84.14 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
hr: UD_Croatian-SET	raw	LAS	not measured	86.11 [85.44, 86.69]	89.74 (Trankit large, UD 2.5; test same size) — MISS	86.95 (Stanza 1.5.1, UD 2.12; test same size) — MISS
hr: UD_Croatian-SET	raw	Lemmas	not measured	92.60 [92.21, 92.96]	97.64 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.60 (Stanza 1.5.1, UD 2.12; test same size) — MISS
hr: UD_Croatian-SET	raw	MLAS	not measured	62.72 [61.75, 63.63]	82.19 (Trankit large, UD 2.5; test same size) — MISS	78.19 (Stanza 1.5.1, UD 2.12; test same size) — MISS
hr: UD_Croatian-SET	raw	Sentences	not measured	94.43 [93.04, 95.73]	99.16 (Trankit base, UD 2.5; test same size) — MISS	97.08 (Stanza 1.5.1, UD 2.12; test same size) — MISS
hr: UD_Croatian-SET	raw	Tokens	not measured	98.83 [98.63, 99.02]	99.96 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.96 (Stanza 1.5.1, UD 2.12; test same size) — MISS
hr: UD_Croatian-SET	raw	UAS	not measured	89.62 [89.01, 90.20]	93.86 (Trankit large, UD 2.5; test same size) — MISS	90.29 (Stanza 1.5.1, UD 2.12; test same size) — MISS
hr: UD_Croatian-SET	raw	UFeats	not measured	83.30 [82.78, 83.82]	96.85 (Trankit large, UD 2.5; test same size) — MISS	95.27 (Stanza 1.5.1, UD 2.12; test same size) — MISS
hr: UD_Croatian-SET	raw	UPOS	not measured	94.15 [93.80, 94.48]	98.58 (Trankit large, UD 2.5; test same size) — MISS	98.21 (Stanza 1.5.1, UD 2.12; test same size) — MISS
hr: UD_Croatian-SET	raw	Words	not measured	98.83 [98.63, 99.02]	99.96 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.96 (Stanza 1.5.1, UD 2.12; test same size) — MISS
hr: UD_Croatian-SET	raw	XPOS	not measured	83.44 [82.88, 83.98]	96.55 (Trankit large, UD 2.5; test same size) — MISS	94.89 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ht: UD_Haitian_Creole-Adolphe	gold	CLAS	not measured	51.35 [49.48, 53.37]	not published	not published
ht: UD_Haitian_Creole-Adolphe	gold	LAS	not measured	54.20 [52.50, 56.13]	60.63 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ht: UD_Haitian_Creole-Adolphe	gold	Lemmas	not measured	98.70 [98.42, 98.96]	99.05 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ht: UD_Haitian_Creole-Adolphe	gold	MLAS	not measured	40.26 [38.56, 42.04]	50.10 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ht: UD_Haitian_Creole-Adolphe	gold	UAS	not measured	59.00 [57.26, 60.95]	64.83 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ht: UD_Haitian_Creole-Adolphe	gold	UFeats	not measured	97.12 [96.65, 97.52]	98.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ht: UD_Haitian_Creole-Adolphe	gold	UPOS	not measured	93.12 [92.47, 93.71]	95.55 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ht: UD_Haitian_Creole-Adolphe	raw	CLAS	not measured	55.04 [53.35, 56.98]	not published	not published
ht: UD_Haitian_Creole-Adolphe	raw	LAS	not measured	57.76 [56.19, 59.57]	60.63 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ht: UD_Haitian_Creole-Adolphe	raw	Lemmas	not measured	98.91 [98.66, 99.15]	99.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
ht: UD_Haitian_Creole-Adolphe	raw	MLAS	not measured	45.00 [43.41, 46.76]	50.13 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ht: UD_Haitian_Creole-Adolphe	raw	Sentences	not measured	97.28 [95.80, 98.64]	98.99 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ht: UD_Haitian_Creole-Adolphe	raw	Tokens	not measured	100.00 [100.00, 100.00]	not published	not published
ht: UD_Haitian_Creole-Adolphe	raw	UAS	not measured	62.04 [60.34, 63.85]	64.82 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ht: UD_Haitian_Creole-Adolphe	raw	UFeats	not measured	97.75 [97.40, 98.07]	97.98 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
ht: UD_Haitian_Creole-Adolphe	raw	UPOS	not measured	94.15 [93.65, 94.59]	95.53 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ht: UD_Haitian_Creole-Adolphe	raw	Words	not measured	100.00 [100.00, 100.00]	99.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
hy: UD_Armenian-ArmTDP	gold	CLAS	not measured	72.45 [70.80, 74.17]	not published	not published
hy: UD_Armenian-ArmTDP	gold	LAS	not measured	76.44 [75.04, 77.94]	87.01 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hy: UD_Armenian-ArmTDP	gold	Lemmas	not measured	92.16 [91.51, 92.79]	97.13 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hy: UD_Armenian-ArmTDP	gold	MLAS	not measured	43.37 [41.73, 45.16]	76.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hy: UD_Armenian-ArmTDP	gold	UAS	not measured	82.51 [81.17, 83.84]	90.79 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hy: UD_Armenian-ArmTDP	gold	UFeats	not measured	71.29 [70.21, 72.45]	94.57 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hy: UD_Armenian-ArmTDP	gold	UPOS	not measured	93.30 [92.71, 93.86]	98.06 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hy: UD_Armenian-ArmTDP	raw	CLAS	not measured	69.55 [67.66, 71.50]	80.91 (Trankit large, UD 2.5; test changed) — MISS	52.52 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
hy: UD_Armenian-ArmTDP	raw	LAS	not measured	72.59 [70.91, 74.32]	86.17 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	61.80 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
hy: UD_Armenian-ArmTDP	raw	Lemmas	not measured	89.43 [88.45, 90.37]	96.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	91.35 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hy: UD_Armenian-ArmTDP	raw	MLAS	not measured	41.47 [39.92, 43.13]	76.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	29.58 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
hy: UD_Armenian-ArmTDP	raw	Sentences	not measured	75.25 [72.09, 78.44]	99.46 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.46 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hy: UD_Armenian-ArmTDP	raw	Tokens	not measured	97.68 [96.98, 98.30]	99.92 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.92 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hy: UD_Armenian-ArmTDP	raw	UAS	not measured	77.81 [76.28, 79.54]	89.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	74.04 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
hy: UD_Armenian-ArmTDP	raw	UFeats	not measured	68.74 [67.65, 69.79]	94.17 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	66.22 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
hy: UD_Armenian-ArmTDP	raw	UPOS	not measured	90.12 [89.22, 90.98]	97.67 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	83.05 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
hy: UD_Armenian-ArmTDP	raw	Words	not measured	96.34 [95.57, 97.03]	99.54 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.48 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hyw: UD_Western_Armenian-ArmTDP	gold	CLAS	not measured	68.29 [66.88, 69.56]	not published	not published
hyw: UD_Western_Armenian-ArmTDP	gold	LAS	not measured	75.20 [74.07, 76.31]	85.14 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hyw: UD_Western_Armenian-ArmTDP	gold	Lemmas	not measured	91.15 [90.60, 91.67]	97.01 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hyw: UD_Western_Armenian-ArmTDP	gold	MLAS	not measured	33.62 [32.35, 34.93]	70.46 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hyw: UD_Western_Armenian-ArmTDP	gold	UAS	not measured	82.46 [81.40, 83.53]	89.65 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hyw: UD_Western_Armenian-ArmTDP	gold	UFeats	not measured	68.53 [67.63, 69.40]	92.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hyw: UD_Western_Armenian-ArmTDP	gold	UPOS	not measured	90.67 [90.07, 91.19]	96.90 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
hyw: UD_Western_Armenian-ArmTDP	raw	CLAS	not measured	64.78 [63.25, 66.27]	77.33 (Stanza 1.5.1, UD 2.12; test changed) — MISS	77.33 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hyw: UD_Western_Armenian-ArmTDP	raw	LAS	not measured	71.14 [69.87, 72.46]	84.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	82.83 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hyw: UD_Western_Armenian-ArmTDP	raw	Lemmas	not measured	88.68 [88.02, 89.34]	96.89 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.70 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hyw: UD_Western_Armenian-ArmTDP	raw	MLAS	not measured	32.06 [30.64, 33.36]	70.21 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	68.89 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hyw: UD_Western_Armenian-ArmTDP	raw	Sentences	not measured	89.14 [86.80, 91.23]	99.56 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.56 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hyw: UD_Western_Armenian-ArmTDP	raw	Tokens	not measured	97.81 [97.49, 98.16]	99.95 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.95 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hyw: UD_Western_Armenian-ArmTDP	raw	UAS	not measured	77.90 [76.61, 79.29]	89.35 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	87.73 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hyw: UD_Western_Armenian-ArmTDP	raw	UFeats	not measured	66.33 [65.43, 67.22]	92.70 (Stanza 1.5.1, UD 2.12; test changed) — MISS	92.70 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hyw: UD_Western_Armenian-ArmTDP	raw	UPOS	not measured	87.57 [86.89, 88.26]	96.81 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.42 (Stanza 1.5.1, UD 2.12; test changed) — MISS
hyw: UD_Western_Armenian-ArmTDP	raw	Words	not measured	96.53 [96.10, 96.98]	99.91 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.91 (Stanza 1.5.1, UD 2.12; test changed) — MISS
id: UD_Indonesian-GSD	gold	AllTags	not measured	74.40 [73.51, 75.36]	89.24 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
id: UD_Indonesian-GSD	gold	CLAS	not measured	63.61 [62.21, 65.22]	not published	not published
id: UD_Indonesian-GSD	gold	LAS	not measured	67.40 [66.10, 68.75]	82.72 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
id: UD_Indonesian-GSD	gold	Lemmas	not measured	95.84 [95.43, 96.23]	98.59 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
id: UD_Indonesian-GSD	gold	MLAS	not measured	50.56 [49.26, 52.04]	73.61 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
id: UD_Indonesian-GSD	gold	UAS	not measured	75.84 [74.67, 77.07]	88.53 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
id: UD_Indonesian-GSD	gold	UFeats	not measured	89.32 [88.69, 89.93]	95.99 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
id: UD_Indonesian-GSD	gold	UPOS	not measured	91.42 [90.75, 92.11]	94.79 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
id: UD_Indonesian-GSD	gold	XPOS	not measured	80.13 [79.27, 80.99]	94.39 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
id: UD_Indonesian-GSD	raw	AllTags	not measured	75.52 [74.56, 76.51]	89.38 (Stanza 1.5.1, UD 2.12; test same size) — MISS	89.38 (Stanza 1.5.1, UD 2.12; test same size) — MISS
id: UD_Indonesian-GSD	raw	CLAS	not measured	69.72 [68.23, 71.40]	78.64 (Trankit base, UD 2.5; test changed) — MISS	76.98 (Stanza 1.5.1, UD 2.12; test same size) — MISS
id: UD_Indonesian-GSD	raw	LAS	not measured	73.87 [72.45, 75.36]	81.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	80.83 (Stanza 1.5.1, UD 2.12; test same size) — MISS
id: UD_Indonesian-GSD	raw	Lemmas	not measured	94.33 [93.77, 94.84]	99.53 (Trankit large, UD 2.5; test changed) — MISS	98.28 (Stanza 1.5.1, UD 2.12; test same size) — MISS
id: UD_Indonesian-GSD	raw	MLAS	not measured	59.56 [57.98, 61.27]	72.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	71.78 (Stanza 1.5.1, UD 2.12; test same size) — MISS
id: UD_Indonesian-GSD	raw	Sentences	not measured	78.47 [74.98, 82.32]	95.54 (Trankit large, UD 2.5; test changed) — MISS	93.04 (Stanza 1.5.1, UD 2.12; test same size) — MISS
id: UD_Indonesian-GSD	raw	Tokens	not measured	99.73 [99.59, 99.85]	99.89 (Trankit large, UD 2.5; test changed) — MISS	99.88 (Stanza 1.5.1, UD 2.12; test same size) — MISS
id: UD_Indonesian-GSD	raw	UAS	not measured	80.64 [79.38, 82.02]	87.65 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	87.05 (Stanza 1.5.1, UD 2.12; test same size) — MISS
id: UD_Indonesian-GSD	raw	UFeats	not measured	88.20 [87.53, 88.85]	96.11 (Trankit large, UD 2.5; test changed) — MISS	95.58 (Stanza 1.5.1, UD 2.12; test same size) — MISS
id: UD_Indonesian-GSD	raw	UPOS	not measured	90.19 [89.45, 90.92]	94.35 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.16 (Stanza 1.5.1, UD 2.12; test same size) — MISS
id: UD_Indonesian-GSD	raw	Words	not measured	96.96 [96.51, 97.36]	99.89 (Trankit large, UD 2.5; test changed) — MISS	99.64 (Stanza 1.5.1, UD 2.12; test same size) — MISS
id: UD_Indonesian-GSD	raw	XPOS	not measured	80.07 [79.20, 80.92]	95.06 (Trankit large, UD 2.5; test changed) — MISS	94.69 (Stanza 1.5.1, UD 2.12; test same size) — MISS
is: UD_Icelandic-IcePaHC	gold	AllTags	not measured	66.58 [66.30, 66.85]	87.48 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
is: UD_Icelandic-IcePaHC	gold	CLAS	not measured	60.44 [59.91, 60.99]	not published	not published
is: UD_Icelandic-IcePaHC	gold	LAS	not measured	65.74 [65.29, 66.19]	83.82 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
is: UD_Icelandic-IcePaHC	gold	Lemmas	not measured	92.47 [92.31, 92.64]	96.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
is: UD_Icelandic-IcePaHC	gold	MLAS	not measured	34.68 [34.22, 35.16]	67.26 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
is: UD_Icelandic-IcePaHC	gold	UAS	not measured	71.65 [71.19, 72.11]	87.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
is: UD_Icelandic-IcePaHC	gold	UFeats	not measured	74.61 [74.33, 74.88]	92.24 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
is: UD_Icelandic-IcePaHC	gold	UPOS	not measured	92.14 [91.99, 92.32]	97.08 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
is: UD_Icelandic-IcePaHC	gold	XPOS	not measured	82.13 [81.89, 82.37]	93.57 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
is: UD_Icelandic-IcePaHC	raw	AllTags	not measured	66.85 [66.56, 67.12]	87.27 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	85.48 (Stanza 1.5.1, UD 2.12; test changed) — MISS
is: UD_Icelandic-IcePaHC	raw	CLAS	not measured	65.66 [65.14, 66.17]	77.27 (Stanza 1.5.1, UD 2.12; test changed) — MISS	77.27 (Stanza 1.5.1, UD 2.12; test changed) — MISS
is: UD_Icelandic-IcePaHC	raw	LAS	not measured	71.34 [70.88, 71.81]	83.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	82.85 (Stanza 1.5.1, UD 2.12; test changed) — MISS
is: UD_Icelandic-IcePaHC	raw	Lemmas	not measured	92.34 [92.17, 92.52]	96.33 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	95.78 (Stanza 1.5.1, UD 2.12; test changed) — MISS
is: UD_Icelandic-IcePaHC	raw	MLAS	not measured	38.66 [38.17, 39.16]	66.86 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	64.78 (Stanza 1.5.1, UD 2.12; test changed) — MISS
is: UD_Icelandic-IcePaHC	raw	Sentences	not measured	89.93 [89.02, 90.80]	93.07 (Stanza 1.5.1, UD 2.12; test changed) — MISS	93.07 (Stanza 1.5.1, UD 2.12; test changed) — MISS
is: UD_Icelandic-IcePaHC	raw	Tokens	not measured	99.76 [99.69, 99.81]	99.90 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.90 (Stanza 1.5.1, UD 2.12; test changed) — MISS
is: UD_Icelandic-IcePaHC	raw	UAS	not measured	77.49 [77.06, 77.95]	87.27 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	86.79 (Stanza 1.5.1, UD 2.12; test changed) — MISS
is: UD_Icelandic-IcePaHC	raw	UFeats	not measured	74.75 [74.44, 75.02]	92.10 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	90.42 (Stanza 1.5.1, UD 2.12; test changed) — MISS
is: UD_Icelandic-IcePaHC	raw	UPOS	not measured	91.85 [91.68, 92.02]	96.92 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.36 (Stanza 1.5.1, UD 2.12; test changed) — MISS
is: UD_Icelandic-IcePaHC	raw	Words	not measured	99.63 [99.56, 99.69]	99.84 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.84 (Stanza 1.5.1, UD 2.12; test changed) — MISS
is: UD_Icelandic-IcePaHC	raw	XPOS	not measured	82.26 [82.02, 82.51]	93.34 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	92.27 (Stanza 1.5.1, UD 2.12; test changed) — MISS
it: UD_Italian-MarkIT	gold	AllTags	89.51 [88.83, 90.21]	89.79 [89.12, 90.43]	92.60 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
it: UD_Italian-MarkIT	gold	CLAS	not measured	72.13 [70.70, 73.64]	not published	not published
it: UD_Italian-MarkIT	gold	LAS	77.27 [76.19, 78.38]	77.63 [76.52, 78.78]	85.54 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
it: UD_Italian-MarkIT	gold	Lemmas	86.37 [85.60, 87.06]	86.38 [85.63, 87.08]	88.62 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
it: UD_Italian-MarkIT	gold	MLAS	not measured	57.58 [56.03, 59.25]	70.84 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
it: UD_Italian-MarkIT	gold	UAS	81.82 [80.77, 82.86]	82.05 [81.01, 83.15]	89.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
it: UD_Italian-MarkIT	gold	UFeats	91.91 [91.27, 92.50]	92.12 [91.51, 92.73]	94.28 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
it: UD_Italian-MarkIT	gold	UPOS	95.69 [95.26, 96.12]	95.81 [95.39, 96.26]	97.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
it: UD_Italian-MarkIT	gold	XPOS	96.31 [95.90, 96.68]	96.26 [95.87, 96.66]	97.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
it: UD_Italian-MarkIT	raw	AllTags	90.13 [89.50, 90.80]	90.50 [89.88, 91.10]	92.37 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	92.34 (Stanza 1.5.1, UD 2.12; test same size) — MISS
it: UD_Italian-MarkIT	raw	CLAS	not measured	77.84 [76.30, 79.29]	74.48 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	74.48 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
it: UD_Italian-MarkIT	raw	LAS	81.12 [79.93, 82.18]	82.22 [81.04, 83.28]	84.79 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	80.63 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
it: UD_Italian-MarkIT	raw	Lemmas	86.46 [85.69, 87.17]	86.65 [85.93, 87.35]	88.31 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	87.08 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
it: UD_Italian-MarkIT	raw	MLAS	not measured	64.34 [62.76, 65.86]	70.25 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	65.35 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
it: UD_Italian-MarkIT	raw	Sentences	90.61 [87.84, 93.57]	90.11 [87.27, 92.93]	99.12 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.12 (Stanza 1.5.1, UD 2.12; test same size) — MISS
it: UD_Italian-MarkIT	raw	Tokens	99.93 [99.86, 99.98]	99.93 [99.86, 99.98]	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS
it: UD_Italian-MarkIT	raw	UAS	85.40 [84.26, 86.44]	86.39 [85.36, 87.29]	88.68 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	85.58 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
it: UD_Italian-MarkIT	raw	UFeats	92.40 [91.81, 93.01]	92.84 [92.29, 93.42]	94.28 (Stanza 1.5.1, UD 2.12; test same size) — MISS	94.28 (Stanza 1.5.1, UD 2.12; test same size) — MISS
it: UD_Italian-MarkIT	raw	UPOS	95.98 [95.54, 96.36]	96.12 [95.75, 96.52]	97.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.29 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
it: UD_Italian-MarkIT	raw	Words	99.73 [99.58, 99.86]	99.73 [99.58, 99.86]	99.67 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	99.67 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
it: UD_Italian-MarkIT	raw	XPOS	96.56 [96.18, 96.92]	96.45 [96.05, 96.80]	97.03 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.34 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
ja: UD_Japanese-GSD	gold	AllTags	not measured	55.45 [54.50, 56.44]	97.37 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ja: UD_Japanese-GSD	gold	CLAS	not measured	48.32 [46.78, 49.96]	not published	not published
ja: UD_Japanese-GSD	gold	LAS	not measured	52.94 [51.62, 54.32]	94.03 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ja: UD_Japanese-GSD	gold	Lemmas	not measured	88.79 [88.18, 89.43]	98.53 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ja: UD_Japanese-GSD	gold	MLAS	not measured	31.47 [30.14, 32.98]	88.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ja: UD_Japanese-GSD	gold	UAS	not measured	60.33 [59.00, 61.70]	94.94 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ja: UD_Japanese-GSD	gold	UFeats	not measured	99.24 [99.08, 99.39]	99.99 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ja: UD_Japanese-GSD	gold	UPOS	not measured	77.54 [76.68, 78.44]	98.61 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ja: UD_Japanese-GSD	gold	XPOS	not measured	60.54 [59.69, 61.44]	97.69 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ja: UD_Japanese-GSD	raw	AllTags	not measured	52.40 [51.39, 53.38]	95.45 (Stanza 1.5.1, UD 2.12; test same size) — MISS	95.45 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ja: UD_Japanese-GSD	raw	CLAS	not measured	52.15 [50.37, 53.93]	84.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS	84.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ja: UD_Japanese-GSD	raw	LAS	not measured	56.76 [55.25, 58.32]	89.29 (Stanza 1.5.1, UD 2.12; test same size) — MISS	89.29 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ja: UD_Japanese-GSD	raw	Lemmas	not measured	87.06 [86.44, 87.73]	96.02 (Stanza 1.5.1, UD 2.12; test same size) — MISS	96.02 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ja: UD_Japanese-GSD	raw	MLAS	not measured	37.05 [35.26, 38.80]	83.86 (Stanza 1.5.1, UD 2.12; test same size) — MISS	83.86 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ja: UD_Japanese-GSD	raw	Sentences	not measured	75.90 [72.12, 79.31]	100.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.72 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ja: UD_Japanese-GSD	raw	Tokens	not measured	96.34 [95.91, 96.79]	97.37 (Stanza 1.5.1, UD 2.12; test same size) — MISS	97.37 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ja: UD_Japanese-GSD	raw	UAS	not measured	62.62 [61.04, 64.19]	90.01 (Stanza 1.5.1, UD 2.12; test same size) — MISS	90.01 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ja: UD_Japanese-GSD	raw	UFeats	not measured	95.62 [95.16, 96.08]	97.36 (Stanza 1.5.1, UD 2.12; test same size) — MISS	97.36 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ja: UD_Japanese-GSD	raw	UPOS	not measured	75.11 [74.17, 76.05]	96.38 (Stanza 1.5.1, UD 2.12; test same size) — MISS	96.38 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ja: UD_Japanese-GSD	raw	Words	not measured	96.34 [95.91, 96.79]	97.37 (Stanza 1.5.1, UD 2.12; test same size) — MISS	97.37 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ja: UD_Japanese-GSD	raw	XPOS	not measured	58.15 [57.31, 59.00]	95.72 (Stanza 1.5.1, UD 2.12; test same size) — MISS	95.72 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ka: UD_Georgian-GLC	gold	AllTags	not measured	71.95 [70.53, 73.31]	92.09 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	gold	CLAS	not measured	74.32 [72.92, 75.66]	not published	not published
ka: UD_Georgian-GLC	gold	LAS	not measured	75.62 [74.36, 76.88]	81.35 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	gold	Lemmas	not measured	86.00 [85.23, 86.81]	94.86 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	gold	MLAS	not measured	47.86 [46.15, 49.53]	71.39 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	gold	UAS	not measured	80.80 [79.59, 82.00]	85.33 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	gold	UFeats	not measured	75.66 [74.50, 76.73]	92.52 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	gold	UPOS	not measured	92.83 [92.27, 93.36]	97.19 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	gold	XPOS	not measured	91.99 [91.29, 92.73]	97.08 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	raw	AllTags	not measured	62.53 [60.91, 64.07]	91.43 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	raw	CLAS	not measured	58.39 [56.54, 60.36]	not published	not published
ka: UD_Georgian-GLC	raw	LAS	not measured	57.09 [55.21, 59.04]	79.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	raw	Lemmas	not measured	75.84 [74.68, 76.94]	94.16 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	raw	MLAS	not measured	38.45 [36.66, 40.33]	70.43 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	raw	Sentences	not measured	87.88 [85.15, 90.48]	95.88 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	raw	Tokens	not measured	99.11 [98.75, 99.40]	not published	not published
ka: UD_Georgian-GLC	raw	UAS	not measured	61.15 [59.26, 63.07]	83.58 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	raw	UFeats	not measured	65.88 [64.51, 67.20]	91.80 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	raw	UPOS	not measured	81.28 [80.19, 82.37]	96.37 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	raw	Words	not measured	87.47 [86.58, 88.31]	99.12 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ka: UD_Georgian-GLC	raw	XPOS	not measured	80.93 [79.77, 82.01]	96.34 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
kk: UD_Kazakh-KTB	gold	AllTags	not measured	24.52 [23.64, 25.46]	not published	not published
kk: UD_Kazakh-KTB	gold	CLAS	not measured	45.66 [44.25, 47.10]	not published	not published
kk: UD_Kazakh-KTB	gold	LAS	not measured	49.32 [47.99, 50.61]	not published	not published
kk: UD_Kazakh-KTB	gold	Lemmas	not measured	58.91 [57.97, 59.84]	not published	not published
kk: UD_Kazakh-KTB	gold	MLAS	not measured	10.68 [9.94, 11.46]	not published	not published
kk: UD_Kazakh-KTB	gold	UAS	not measured	67.55 [66.13, 68.93]	not published	not published
kk: UD_Kazakh-KTB	gold	UFeats	not measured	46.86 [45.91, 47.77]	not published	not published
kk: UD_Kazakh-KTB	gold	UPOS	not measured	50.89 [49.90, 51.85]	not published	not published
kk: UD_Kazakh-KTB	gold	XPOS	not measured	58.02 [56.89, 59.15]	not published	not published
kk: UD_Kazakh-KTB	raw	AllTags	not measured	32.17 [31.28, 33.00]	74.50 (Stanza 1.5.1, UD 2.12; test same size) — MISS	74.50 (Stanza 1.5.1, UD 2.12; test same size) — MISS
kk: UD_Kazakh-KTB	raw	CLAS	not measured	32.15 [30.90, 33.51]	49.45 (Stanza 1.5.1, UD 2.12; test same size) — MISS	49.45 (Stanza 1.5.1, UD 2.12; test same size) — MISS
kk: UD_Kazakh-KTB	raw	LAS	not measured	33.79 [32.50, 35.13]	51.38 (Stanza 1.5.1, UD 2.12; test same size) — MISS	51.38 (Stanza 1.5.1, UD 2.12; test same size) — MISS
kk: UD_Kazakh-KTB	raw	Lemmas	not measured	56.21 [55.20, 57.18]	89.21 (Stanza 1.5.1, UD 2.12; test same size) — MISS	89.21 (Stanza 1.5.1, UD 2.12; test same size) — MISS
kk: UD_Kazakh-KTB	raw	MLAS	not measured	8.37 [7.67, 9.03]	38.40 (Stanza 1.5.1, UD 2.12; test same size) — MISS	38.40 (Stanza 1.5.1, UD 2.12; test same size) — MISS
kk: UD_Kazakh-KTB	raw	Sentences	not measured	18.15 [15.63, 20.76]	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS
kk: UD_Kazakh-KTB	raw	Tokens	not measured	97.45 [96.91, 97.93]	99.42 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.42 (Stanza 1.5.1, UD 2.12; test same size) — MISS
kk: UD_Kazakh-KTB	raw	UAS	not measured	45.81 [44.34, 47.37]	60.55 (Stanza 1.5.1, UD 2.12; test same size) — MISS	60.55 (Stanza 1.5.1, UD 2.12; test same size) — MISS
kk: UD_Kazakh-KTB	raw	UFeats	not measured	45.88 [44.91, 46.76]	78.70 (Stanza 1.5.1, UD 2.12; test same size) — MISS	78.70 (Stanza 1.5.1, UD 2.12; test same size) — MISS
kk: UD_Kazakh-KTB	raw	UPOS	not measured	53.41 [52.43, 54.35]	85.58 (Stanza 1.5.1, UD 2.12; test same size) — MISS	85.58 (Stanza 1.5.1, UD 2.12; test same size) — MISS
kk: UD_Kazakh-KTB	raw	Words	not measured	96.99 [96.44, 97.50]	96.85 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	96.85 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
kk: UD_Kazakh-KTB	raw	XPOS	not measured	63.99 [62.97, 65.01]	86.15 (Stanza 1.5.1, UD 2.12; test same size) — MISS	86.15 (Stanza 1.5.1, UD 2.12; test same size) — MISS
kmr: UD_Northern_Kurdish-Kurmanji	gold	AllTags	not measured	13.72 [13.02, 14.37]	not published	not published
kmr: UD_Northern_Kurdish-Kurmanji	gold	CLAS	not measured	44.92 [43.24, 46.64]	not published	not published
kmr: UD_Northern_Kurdish-Kurmanji	gold	LAS	not measured	49.91 [48.41, 51.34]	not published	not published
kmr: UD_Northern_Kurdish-Kurmanji	gold	Lemmas	not measured	62.32 [61.26, 63.37]	not published	not published
kmr: UD_Northern_Kurdish-Kurmanji	gold	MLAS	not measured	4.98 [4.42, 5.54]	not published	not published
kmr: UD_Northern_Kurdish-Kurmanji	gold	UAS	not measured	63.32 [61.80, 64.85]	not published	not published
kmr: UD_Northern_Kurdish-Kurmanji	gold	UFeats	not measured	42.46 [41.64, 43.30]	not published	not published
kmr: UD_Northern_Kurdish-Kurmanji	gold	UPOS	not measured	49.90 [48.87, 50.85]	not published	not published
kmr: UD_Northern_Kurdish-Kurmanji	gold	XPOS	not measured	45.00 [44.06, 45.88]	not published	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	AllTags	not measured	21.91 [21.19, 22.61]	52.27 (Trankit large, UD 2.5; test same size) — MISS	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	CLAS	not measured	41.35 [39.52, 43.23]	25.57 (Trankit large, UD 2.5; test same size) — within or ahead	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	LAS	not measured	46.20 [44.40, 47.97]	29.89 (Trankit large, UD 2.5; test same size) — within or ahead	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	Lemmas	not measured	63.13 [62.13, 64.19]	57.63 (Trankit large, UD 2.5; test same size) — within or ahead	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	MLAS	not measured	5.53 [4.93, 6.12]	9.04 (Trankit large, UD 2.5; test same size) — MISS	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	Sentences	not measured	47.71 [43.89, 51.46]	91.50 (Trankit large, UD 2.5; test same size) — MISS	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	Tokens	not measured	96.59 [96.08, 97.08]	94.95 (Trankit large, UD 2.5; test same size) — within or ahead	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	UAS	not measured	55.20 [53.33, 57.16]	37.12 (Trankit large, UD 2.5; test same size) — within or ahead	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	UFeats	not measured	43.71 [42.81, 44.58]	57.15 (Trankit large, UD 2.5; test same size) — MISS	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	UPOS	not measured	53.90 [52.84, 54.98]	75.07 (Trankit large, UD 2.5; test same size) — MISS	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	Words	not measured	96.09 [95.57, 96.57]	94.63 (Trankit large, UD 2.5; test same size) — within or ahead	not published
kmr: UD_Northern_Kurdish-Kurmanji	raw	XPOS	not measured	53.43 [52.40, 54.38]	74.16 (Trankit large, UD 2.5; test same size) — MISS	not published
ko: UD_Korean-Kaist	gold	AllTags	not measured	50.87 [50.24, 51.48]	87.60 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ko: UD_Korean-Kaist	gold	CLAS	not measured	64.84 [64.16, 65.57]	not published	not published
ko: UD_Korean-Kaist	gold	LAS	not measured	68.13 [67.42, 68.83]	86.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ko: UD_Korean-Kaist	gold	Lemmas	not measured	82.01 [81.55, 82.51]	94.39 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ko: UD_Korean-Kaist	gold	MLAS	not measured	54.48 [53.71, 55.22]	82.88 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ko: UD_Korean-Kaist	gold	UAS	not measured	76.81 [76.13, 77.49]	88.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ko: UD_Korean-Kaist	gold	UPOS	not measured	83.77 [83.31, 84.20]	96.21 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ko: UD_Korean-Kaist	gold	XPOS	not measured	53.61 [53.00, 54.24]	87.81 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ko: UD_Korean-Kaist	raw	AllTags	not measured	55.15 [54.56, 55.79]	88.07 (Trankit large, UD 2.5; test same size) — MISS	85.81 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ko: UD_Korean-Kaist	raw	CLAS	not measured	72.10 [71.40, 72.85]	86.37 (Trankit large, UD 2.5; test same size) — MISS	83.65 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ko: UD_Korean-Kaist	raw	LAS	not measured	74.17 [73.47, 74.90]	88.22 (Trankit large, UD 2.5; test same size) — MISS	85.50 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ko: UD_Korean-Kaist	raw	Lemmas	not measured	82.88 [82.41, 83.38]	94.39 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.10 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ko: UD_Korean-Kaist	raw	MLAS	not measured	62.12 [61.35, 62.90]	83.56 (Trankit large, UD 2.5; test same size) — MISS	80.93 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ko: UD_Korean-Kaist	raw	Sentences	not measured	92.51 [91.52, 93.49]	100.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.93 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ko: UD_Korean-Kaist	raw	Tokens	not measured	99.90 [99.84, 99.95]	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ko: UD_Korean-Kaist	raw	UAS	not measured	80.66 [79.98, 81.38]	90.00 (Trankit large, UD 2.5; test same size) — MISS	87.63 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ko: UD_Korean-Kaist	raw	UPOS	not measured	85.53 [85.09, 85.97]	96.21 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	95.74 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ko: UD_Korean-Kaist	raw	Words	not measured	99.90 [99.84, 99.95]	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ko: UD_Korean-Kaist	raw	XPOS	not measured	57.88 [57.27, 58.51]	88.07 (Trankit large, UD 2.5; test same size) — MISS	85.81 (Stanza 1.5.1, UD 2.12; test same size) — MISS
koi: UD_Komi_Permyak-UH	gold	AllTags	not measured	17.39 [15.54, 19.26]	not published	not published
koi: UD_Komi_Permyak-UH	gold	CLAS	not measured	23.79 [19.78, 28.52]	not published	not published
koi: UD_Komi_Permyak-UH	gold	LAS	not measured	30.79 [26.88, 35.53]	not published	not published
koi: UD_Komi_Permyak-UH	gold	Lemmas	not measured	60.58 [56.73, 63.70]	not published	not published
koi: UD_Komi_Permyak-UH	gold	MLAS	not measured	4.98 [3.51, 6.81]	not published	not published
koi: UD_Komi_Permyak-UH	gold	UAS	not measured	50.61 [45.71, 56.22]	not published	not published
koi: UD_Komi_Permyak-UH	gold	UFeats	not measured	44.96 [41.69, 47.92]	not published	not published
koi: UD_Komi_Permyak-UH	gold	UPOS	not measured	54.71 [51.54, 57.78]	not published	not published
koi: UD_Komi_Permyak-UH	gold	XPOS	not measured	17.39 [15.54, 19.26]	not published	not published
koi: UD_Komi_Permyak-UH	raw	AllTags	not measured	17.39 [15.54, 19.26]	not published	not published
koi: UD_Komi_Permyak-UH	raw	CLAS	not measured	27.03 [22.60, 32.05]	not published	not published
koi: UD_Komi_Permyak-UH	raw	LAS	not measured	33.78 [29.41, 38.81]	not published	not published
koi: UD_Komi_Permyak-UH	raw	Lemmas	not measured	61.35 [57.52, 64.60]	not published	not published
koi: UD_Komi_Permyak-UH	raw	MLAS	not measured	4.10 [2.64, 5.81]	not published	not published
koi: UD_Komi_Permyak-UH	raw	Sentences	not measured	75.38 [66.34, 82.90]	not published	not published
koi: UD_Komi_Permyak-UH	raw	Tokens	not measured	100.00 [100.00, 100.00]	not published	not published
koi: UD_Komi_Permyak-UH	raw	UAS	not measured	54.60 [49.09, 60.45]	not published	not published
koi: UD_Komi_Permyak-UH	raw	UFeats	not measured	45.63 [42.91, 48.31]	not published	not published
koi: UD_Komi_Permyak-UH	raw	UPOS	not measured	50.50 [47.91, 52.99]	not published	not published
koi: UD_Komi_Permyak-UH	raw	Words	not measured	100.00 [100.00, 100.00]	not published	not published
koi: UD_Komi_Permyak-UH	raw	XPOS	not measured	17.39 [15.54, 19.26]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	gold	AllTags	not measured	6.93 [6.30, 7.55]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	gold	CLAS	not measured	20.80 [19.60, 22.09]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	gold	LAS	not measured	25.75 [24.50, 27.15]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	gold	Lemmas	not measured	60.89 [59.87, 61.84]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	gold	MLAS	not measured	2.24 [1.85, 2.67]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	gold	UAS	not measured	45.10 [43.31, 46.85]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	gold	UFeats	not measured	12.17 [11.45, 12.95]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	gold	UPOS	not measured	26.84 [25.76, 27.89]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	gold	XPOS	not measured	32.46 [31.47, 33.42]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	AllTags	not measured	12.96 [12.23, 13.72]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	CLAS	not measured	9.99 [9.02, 11.00]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	LAS	not measured	12.68 [11.68, 13.80]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	Lemmas	not measured	60.23 [59.20, 61.18]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	MLAS	not measured	0.89 [0.64, 1.16]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	Sentences	not measured	1.45 [0.47, 2.66]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	Tokens	not measured	99.91 [99.82, 99.98]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	UAS	not measured	22.17 [20.60, 23.81]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	UFeats	not measured	20.18 [19.30, 21.14]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	UPOS	not measured	36.32 [35.14, 37.42]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	Words	not measured	99.24 [98.96, 99.51]	not published	not published
kpv: UD_Komi_Zyrian-Lattice	raw	XPOS	not measured	37.42 [36.41, 38.43]	not published	not published
ky: UD_Kyrgyz-KTMU	gold	AllTags	not measured	61.92 [60.81, 63.04]	73.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ky: UD_Kyrgyz-KTMU	gold	CLAS	not measured	61.76 [60.54, 62.98]	not published	not published
ky: UD_Kyrgyz-KTMU	gold	LAS	not measured	65.35 [64.24, 66.42]	74.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ky: UD_Kyrgyz-KTMU	gold	Lemmas	not measured	80.51 [79.69, 81.38]	89.39 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ky: UD_Kyrgyz-KTMU	gold	MLAS	not measured	38.51 [37.17, 39.79]	54.61 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ky: UD_Kyrgyz-KTMU	gold	UAS	not measured	78.82 [77.89, 79.75]	84.78 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ky: UD_Kyrgyz-KTMU	gold	UFeats	not measured	66.43 [65.37, 67.55]	77.98 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ky: UD_Kyrgyz-KTMU	gold	UPOS	not measured	88.87 [88.18, 89.53]	91.66 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ky: UD_Kyrgyz-KTMU	gold	XPOS	not measured	88.72 [88.07, 89.39]	91.06 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ky: UD_Kyrgyz-KTMU	raw	AllTags	not measured	61.82 [60.78, 62.86]	72.81 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	57.91 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
ky: UD_Kyrgyz-KTMU	raw	CLAS	not measured	64.75 [63.38, 66.06]	52.60 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead	52.60 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
ky: UD_Kyrgyz-KTMU	raw	LAS	not measured	67.79 [66.50, 68.97]	73.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	58.77 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
ky: UD_Kyrgyz-KTMU	raw	Lemmas	not measured	79.55 [78.75, 80.43]	88.71 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	88.09 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ky: UD_Kyrgyz-KTMU	raw	MLAS	not measured	40.79 [39.41, 42.11]	54.17 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	28.47 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
ky: UD_Kyrgyz-KTMU	raw	Sentences	not measured	92.70 [91.28, 94.09]	98.14 (Stanza 1.5.1, UD 2.12; test changed) — MISS	98.14 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ky: UD_Kyrgyz-KTMU	raw	Tokens	not measured	97.59 [97.23, 97.93]	99.06 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.06 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ky: UD_Kyrgyz-KTMU	raw	UAS	not measured	79.63 [78.60, 80.52]	84.01 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	74.95 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
ky: UD_Kyrgyz-KTMU	raw	UFeats	not measured	66.26 [65.21, 67.25]	77.29 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	60.22 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
ky: UD_Kyrgyz-KTMU	raw	UPOS	not measured	87.18 [86.43, 87.88]	90.96 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	87.65 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
ky: UD_Kyrgyz-KTMU	raw	Words	not measured	97.59 [97.23, 97.93]	99.25 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.06 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ky: UD_Kyrgyz-KTMU	raw	XPOS	not measured	87.55 [86.88, 88.18]	90.35 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	87.94 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
la: UD_Latin-LLCT	gold	AllTags	not measured	70.96 [70.03, 71.97]	96.84 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
la: UD_Latin-LLCT	gold	CLAS	not measured	77.30 [75.92, 78.81]	not published	not published
la: UD_Latin-LLCT	gold	LAS	not measured	80.93 [79.78, 82.10]	94.07 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
la: UD_Latin-LLCT	gold	Lemmas	not measured	95.42 [94.99, 95.85]	97.80 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
la: UD_Latin-LLCT	gold	MLAS	not measured	51.35 [49.65, 53.15]	88.66 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
la: UD_Latin-LLCT	gold	UAS	not measured	83.95 [82.93, 84.98]	95.05 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
la: UD_Latin-LLCT	gold	UFeats	not measured	75.63 [74.78, 76.57]	97.12 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
la: UD_Latin-LLCT	gold	UPOS	not measured	96.38 [96.09, 96.67]	99.78 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
la: UD_Latin-LLCT	gold	XPOS	not measured	76.59 [75.69, 77.53]	97.05 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
la: UD_Latin-LLCT	raw	AllTags	not measured	72.20 [71.18, 73.34]	96.83 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.47 (Stanza 1.5.1, UD 2.12; test changed) — MISS
la: UD_Latin-LLCT	raw	CLAS	not measured	79.91 [78.42, 81.41]	93.53 (Stanza 1.5.1, UD 2.12; test changed) — MISS	93.53 (Stanza 1.5.1, UD 2.12; test changed) — MISS
la: UD_Latin-LLCT	raw	LAS	not measured	83.30 [82.10, 84.52]	94.88 (Stanza 1.5.1, UD 2.12; test changed) — MISS	94.88 (Stanza 1.5.1, UD 2.12; test changed) — MISS
la: UD_Latin-LLCT	raw	Lemmas	not measured	95.64 [95.22, 96.06]	98.09 (Stanza 1.5.1, UD 2.12; test changed) — MISS	98.09 (Stanza 1.5.1, UD 2.12; test changed) — MISS
la: UD_Latin-LLCT	raw	MLAS	not measured	53.58 [51.84, 55.42]	89.49 (Stanza 1.5.1, UD 2.12; test changed) — MISS	89.49 (Stanza 1.5.1, UD 2.12; test changed) — MISS
la: UD_Latin-LLCT	raw	Sentences	not measured	88.69 [86.82, 90.62]	99.49 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.32 (Stanza 1.5.1, UD 2.12; test changed) — MISS
la: UD_Latin-LLCT	raw	Tokens	not measured	99.73 [99.62, 99.82]	99.99 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.99 (Stanza 1.5.1, UD 2.12; test changed) — MISS
la: UD_Latin-LLCT	raw	UAS	not measured	86.01 [84.90, 87.13]	96.13 (Stanza 1.5.1, UD 2.12; test changed) — MISS	96.13 (Stanza 1.5.1, UD 2.12; test changed) — MISS
la: UD_Latin-LLCT	raw	UFeats	not measured	75.55 [74.62, 76.55]	97.12 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.79 (Stanza 1.5.1, UD 2.12; test changed) — MISS
la: UD_Latin-LLCT	raw	UPOS	not measured	96.72 [96.43, 97.01]	99.77 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.57 (Stanza 1.5.1, UD 2.12; test changed) — MISS
la: UD_Latin-LLCT	raw	Words	not measured	99.71 [99.60, 99.81]	99.99 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.99 (Stanza 1.5.1, UD 2.12; test changed) — MISS
la: UD_Latin-LLCT	raw	XPOS	not measured	77.82 [76.97, 78.83]	97.05 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.65 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lij: UD_Ligurian-GLT	gold	CLAS	not measured	25.63 [23.69, 27.63]	not published	not published
lij: UD_Ligurian-GLT	gold	LAS	not measured	36.41 [34.59, 38.31]	not published	not published
lij: UD_Ligurian-GLT	gold	Lemmas	not measured	72.29 [70.97, 73.49]	not published	not published
lij: UD_Ligurian-GLT	gold	MLAS	not measured	4.68 [3.83, 5.43]	not published	not published
lij: UD_Ligurian-GLT	gold	UAS	not measured	54.80 [52.79, 56.88]	not published	not published
lij: UD_Ligurian-GLT	gold	UFeats	not measured	45.14 [43.85, 46.38]	not published	not published
lij: UD_Ligurian-GLT	gold	UPOS	not measured	56.57 [55.42, 57.72]	not published	not published
lij: UD_Ligurian-GLT	raw	CLAS	not measured	19.82 [18.05, 21.74]	60.33 (Stanza 1.5.1, UD 2.12; test same size) — MISS	60.33 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lij: UD_Ligurian-GLT	raw	LAS	not measured	25.76 [24.05, 27.47]	69.18 (Stanza 1.5.1, UD 2.12; test same size) — MISS	69.18 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lij: UD_Ligurian-GLT	raw	Lemmas	not measured	61.84 [60.48, 63.20]	92.68 (Stanza 1.5.1, UD 2.12; test same size) — MISS	92.68 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lij: UD_Ligurian-GLT	raw	MLAS	not measured	3.31 [2.61, 3.97]	51.24 (Stanza 1.5.1, UD 2.12; test same size) — MISS	51.24 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lij: UD_Ligurian-GLT	raw	Sentences	not measured	34.74 [28.95, 40.53]	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lij: UD_Ligurian-GLT	raw	Tokens	not measured	89.31 [88.32, 90.26]	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lij: UD_Ligurian-GLT	raw	UAS	not measured	37.84 [35.73, 39.98]	77.61 (Stanza 1.5.1, UD 2.12; test same size) — MISS	77.61 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lij: UD_Ligurian-GLT	raw	UFeats	not measured	38.11 [36.98, 39.19]	88.25 (Stanza 1.5.1, UD 2.12; test same size) — MISS	88.25 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lij: UD_Ligurian-GLT	raw	UPOS	not measured	47.86 [46.61, 49.07]	89.14 (Stanza 1.5.1, UD 2.12; test same size) — MISS	89.14 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lij: UD_Ligurian-GLT	raw	Words	not measured	81.74 [80.53, 83.00]	98.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS	98.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lt: UD_Lithuanian-ALKSNIS	gold	AllTags	not measured	67.88 [66.97, 68.88]	89.46 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lt: UD_Lithuanian-ALKSNIS	gold	CLAS	not measured	69.77 [68.26, 71.06]	not published	not published
lt: UD_Lithuanian-ALKSNIS	gold	LAS	not measured	72.74 [71.48, 73.89]	79.92 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lt: UD_Lithuanian-ALKSNIS	gold	Lemmas	not measured	80.46 [79.60, 81.34]	93.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lt: UD_Lithuanian-ALKSNIS	gold	MLAS	not measured	41.85 [40.64, 43.11]	68.90 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lt: UD_Lithuanian-ALKSNIS	gold	UAS	not measured	78.38 [77.13, 79.56]	83.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lt: UD_Lithuanian-ALKSNIS	gold	UFeats	not measured	72.11 [71.26, 73.06]	91.19 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lt: UD_Lithuanian-ALKSNIS	gold	UPOS	not measured	88.95 [88.27, 89.65]	96.09 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lt: UD_Lithuanian-ALKSNIS	gold	XPOS	not measured	72.57 [71.68, 73.49]	90.39 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lt: UD_Lithuanian-ALKSNIS	raw	AllTags	not measured	69.48 [68.60, 70.43]	93.30 (Trankit large, UD 2.5; test same size) — MISS	85.54 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lt: UD_Lithuanian-ALKSNIS	raw	CLAS	not measured	74.53 [73.23, 75.77]	86.66 (Trankit large, UD 2.5; test same size) — MISS	70.23 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
lt: UD_Lithuanian-ALKSNIS	raw	LAS	not measured	76.39 [75.20, 77.55]	87.67 (Trankit large, UD 2.5; test same size) — MISS	72.75 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
lt: UD_Lithuanian-ALKSNIS	raw	Lemmas	not measured	81.55 [80.75, 82.31]	94.30 (Trankit large, UD 2.5; test same size) — MISS	92.95 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lt: UD_Lithuanian-ALKSNIS	raw	MLAS	not measured	46.90 [45.62, 48.09]	79.86 (Trankit large, UD 2.5; test same size) — MISS	60.53 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lt: UD_Lithuanian-ALKSNIS	raw	Sentences	not measured	81.03 [77.95, 83.57]	95.72 (Trankit large, UD 2.5; test same size) — MISS	89.93 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lt: UD_Lithuanian-ALKSNIS	raw	Tokens	not measured	99.71 [99.57, 99.82]	99.94 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.94 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lt: UD_Lithuanian-ALKSNIS	raw	UAS	not measured	81.67 [80.47, 82.76]	90.48 (Trankit large, UD 2.5; test same size) — MISS	77.82 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
lt: UD_Lithuanian-ALKSNIS	raw	UFeats	not measured	73.62 [72.76, 74.51]	94.46 (Trankit large, UD 2.5; test same size) — MISS	88.16 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lt: UD_Lithuanian-ALKSNIS	raw	UPOS	not measured	89.59 [88.93, 90.24]	97.45 (Trankit large, UD 2.5; test same size) — MISS	93.71 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lt: UD_Lithuanian-ALKSNIS	raw	Words	not measured	99.71 [99.57, 99.82]	99.94 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.94 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lt: UD_Lithuanian-ALKSNIS	raw	XPOS	not measured	74.08 [73.23, 74.96]	93.98 (Trankit large, UD 2.5; test same size) — MISS	86.48 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lv: UD_Latvian-LVTB	gold	AllTags	not measured	62.76 [62.26, 63.23]	92.27 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lv: UD_Latvian-LVTB	gold	CLAS	not measured	74.70 [73.92, 75.41]	not published	not published
lv: UD_Latvian-LVTB	gold	LAS	not measured	78.42 [77.72, 79.07]	87.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lv: UD_Latvian-LVTB	gold	Lemmas	not measured	90.81 [90.48, 91.14]	97.48 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lv: UD_Latvian-LVTB	gold	MLAS	not measured	50.21 [49.42, 51.02]	80.23 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lv: UD_Latvian-LVTB	gold	UAS	not measured	83.67 [83.00, 84.27]	90.37 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lv: UD_Latvian-LVTB	gold	UFeats	not measured	78.48 [78.06, 78.91]	95.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lv: UD_Latvian-LVTB	gold	UPOS	not measured	92.03 [91.73, 92.32]	98.09 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lv: UD_Latvian-LVTB	gold	XPOS	not measured	65.93 [65.43, 66.42]	92.69 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lv: UD_Latvian-LVTB	raw	AllTags	not measured	64.02 [63.51, 64.51]	91.60 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	89.29 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lv: UD_Latvian-LVTB	raw	CLAS	not measured	79.91 [79.15, 80.62]	89.78 (Trankit large, UD 2.5; test changed) — MISS	83.37 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lv: UD_Latvian-LVTB	raw	LAS	not measured	82.85 [82.18, 83.48]	91.25 (Trankit large, UD 2.5; test changed) — MISS	85.77 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lv: UD_Latvian-LVTB	raw	Lemmas	not measured	90.83 [90.49, 91.16]	96.81 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.12 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lv: UD_Latvian-LVTB	raw	MLAS	not measured	56.14 [55.35, 56.98]	82.69 (Trankit large, UD 2.5; test changed) — MISS	76.71 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lv: UD_Latvian-LVTB	raw	Sentences	not measured	94.39 [93.46, 95.24]	99.10 (Trankit base, UD 2.5; test changed) — MISS	98.15 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lv: UD_Latvian-LVTB	raw	Tokens	not measured	98.79 [98.60, 98.97]	99.81 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.81 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lv: UD_Latvian-LVTB	raw	UAS	not measured	87.56 [86.95, 88.15]	93.63 (Trankit large, UD 2.5; test changed) — MISS	88.91 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lv: UD_Latvian-LVTB	raw	UFeats	not measured	79.94 [79.53, 80.40]	95.28 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.73 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lv: UD_Latvian-LVTB	raw	UPOS	not measured	91.98 [91.63, 92.29]	97.61 (Trankit large, UD 2.5; test changed) — MISS	96.70 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lv: UD_Latvian-LVTB	raw	Words	not measured	98.79 [98.60, 98.97]	99.81 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.81 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lv: UD_Latvian-LVTB	raw	XPOS	not measured	66.51 [65.99, 66.99]	92.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	89.72 (Stanza 1.5.1, UD 2.12; test changed) — MISS
lzh: UD_Classical_Chinese-Kyoto	gold	AllTags	not measured	54.93 [54.32, 55.53]	89.74 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lzh: UD_Classical_Chinese-Kyoto	gold	CLAS	not measured	63.68 [62.84, 64.54]	not published	not published
lzh: UD_Classical_Chinese-Kyoto	gold	LAS	not measured	63.79 [62.96, 64.62]	79.13 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lzh: UD_Classical_Chinese-Kyoto	gold	Lemmas	not measured	98.51 [98.36, 98.66]	99.53 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lzh: UD_Classical_Chinese-Kyoto	gold	MLAS	not measured	53.02 [52.23, 53.89]	75.29 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lzh: UD_Classical_Chinese-Kyoto	gold	UAS	not measured	72.31 [71.47, 73.16]	84.45 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lzh: UD_Classical_Chinese-Kyoto	gold	UFeats	not measured	85.19 [84.71, 85.62]	94.56 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lzh: UD_Classical_Chinese-Kyoto	gold	UPOS	not measured	84.48 [84.01, 84.93]	93.21 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lzh: UD_Classical_Chinese-Kyoto	gold	XPOS	not measured	58.82 [58.24, 59.41]	92.07 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
lzh: UD_Classical_Chinese-Kyoto	raw	AllTags	not measured	54.83 [54.26, 55.39]	89.98 (Trankit large, UD 2.5; test changed) — MISS	85.89 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lzh: UD_Classical_Chinese-Kyoto	raw	CLAS	not measured	63.95 [63.12, 64.79]	75.60 (Trankit large, UD 2.5; test changed) — MISS	64.54 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
lzh: UD_Classical_Chinese-Kyoto	raw	LAS	not measured	64.12 [63.30, 64.96]	76.82 (Trankit large, UD 2.5; test changed) — MISS	65.80 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lzh: UD_Classical_Chinese-Kyoto	raw	Lemmas	not measured	96.66 [96.40, 96.91]	99.67 (Trankit large, UD 2.5; test changed) — MISS	97.63 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lzh: UD_Classical_Chinese-Kyoto	raw	MLAS	not measured	54.27 [53.49, 55.12]	73.16 (Trankit large, UD 2.5; test changed) — MISS	61.94 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lzh: UD_Classical_Chinese-Kyoto	raw	Sentences	not measured	94.40 [93.81, 94.96]	70.58 (Trankit large, UD 2.5; test changed) — within or ahead	49.57 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
lzh: UD_Classical_Chinese-Kyoto	raw	Tokens	not measured	97.90 [97.67, 98.11]	99.70 (Trankit large, UD 2.5; test changed) — MISS	97.85 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
lzh: UD_Classical_Chinese-Kyoto	raw	UAS	not measured	71.96 [71.14, 72.75]	82.03 (Trankit large, UD 2.5; test changed) — MISS	71.32 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
lzh: UD_Classical_Chinese-Kyoto	raw	UFeats	not measured	84.25 [83.79, 84.68]	94.43 (Trankit large, UD 2.5; test changed) — MISS	91.38 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lzh: UD_Classical_Chinese-Kyoto	raw	UPOS	not measured	84.19 [83.73, 84.68]	92.89 (Trankit large, UD 2.5; test changed) — MISS	89.16 (Stanza 1.5.1, UD 2.12; test same size) — MISS
lzh: UD_Classical_Chinese-Kyoto	raw	Words	not measured	97.90 [97.67, 98.11]	99.70 (Trankit large, UD 2.5; test changed) — MISS	97.85 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
lzh: UD_Classical_Chinese-Kyoto	raw	XPOS	not measured	58.63 [58.06, 59.17]	91.90 (Trankit large, UD 2.5; test changed) — MISS	88.17 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mdf: UD_Moksha-JR	gold	AllTags	not measured	12.50 [11.26, 13.69]	not published	not published
mdf: UD_Moksha-JR	gold	CLAS	not measured	19.82 [18.27, 21.49]	not published	not published
mdf: UD_Moksha-JR	gold	LAS	not measured	25.61 [23.95, 27.43]	not published	not published
mdf: UD_Moksha-JR	gold	Lemmas	not measured	54.49 [53.07, 55.74]	not published	not published
mdf: UD_Moksha-JR	gold	MLAS	not measured	3.51 [2.85, 4.21]	not published	not published
mdf: UD_Moksha-JR	gold	UAS	not measured	46.61 [44.25, 49.02]	not published	not published
mdf: UD_Moksha-JR	gold	UFeats	not measured	33.08 [31.94, 34.17]	not published	not published
mdf: UD_Moksha-JR	gold	UPOS	not measured	48.38 [47.03, 49.73]	not published	not published
mdf: UD_Moksha-JR	gold	XPOS	not measured	33.10 [31.59, 34.54]	not published	not published
mdf: UD_Moksha-JR	raw	AllTags	not measured	21.77 [20.35, 23.14]	not published	not published
mdf: UD_Moksha-JR	raw	CLAS	not measured	25.35 [23.57, 27.09]	not published	not published
mdf: UD_Moksha-JR	raw	LAS	not measured	30.66 [28.78, 32.54]	not published	not published
mdf: UD_Moksha-JR	raw	Lemmas	not measured	55.83 [54.40, 57.02]	not published	not published
mdf: UD_Moksha-JR	raw	MLAS	not measured	5.54 [4.72, 6.43]	not published	not published
mdf: UD_Moksha-JR	raw	Sentences	not measured	51.73 [46.72, 57.11]	not published	not published
mdf: UD_Moksha-JR	raw	Tokens	not measured	99.93 [99.82, 100.00]	not published	not published
mdf: UD_Moksha-JR	raw	UAS	not measured	51.48 [49.02, 53.81]	not published	not published
mdf: UD_Moksha-JR	raw	UFeats	not measured	38.54 [37.34, 39.79]	not published	not published
mdf: UD_Moksha-JR	raw	UPOS	not measured	52.79 [51.42, 54.27]	not published	not published
mdf: UD_Moksha-JR	raw	Words	not measured	99.79 [99.58, 99.95]	not published	not published
mdf: UD_Moksha-JR	raw	XPOS	not measured	41.83 [40.35, 43.45]	not published	not published
mr: UD_Marathi-UFAL	gold	CLAS	not measured	57.49 [49.18, 65.92]	not published	not published
mr: UD_Marathi-UFAL	gold	LAS	not measured	63.59 [55.41, 71.76]	64.81 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
mr: UD_Marathi-UFAL	gold	Lemmas	not measured	73.30 [69.70, 77.23]	87.86 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
mr: UD_Marathi-UFAL	gold	MLAS	not measured	4.93 [2.60, 7.48]	40.50 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
mr: UD_Marathi-UFAL	gold	UAS	not measured	74.76 [66.75, 82.95]	73.06 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
mr: UD_Marathi-UFAL	gold	UFeats	not measured	38.59 [34.34, 42.44]	76.94 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
mr: UD_Marathi-UFAL	gold	UPOS	not measured	80.58 [76.30, 84.38]	88.59 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
mr: UD_Marathi-UFAL	raw	CLAS	not measured	47.72 [40.09, 55.63]	59.67 (Trankit large, UD 2.5; test same size) — MISS	54.73 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
mr: UD_Marathi-UFAL	raw	LAS	not measured	51.52 [42.56, 60.16]	63.36 (Trankit large, UD 2.5; test same size) — MISS	59.56 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
mr: UD_Marathi-UFAL	raw	Lemmas	not measured	69.54 [65.28, 74.07]	84.67 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	82.84 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mr: UD_Marathi-UFAL	raw	MLAS	not measured	6.22 [3.70, 9.22]	38.10 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	37.04 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mr: UD_Marathi-UFAL	raw	Sentences	not measured	83.15 [72.09, 92.31]	92.63 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	89.36 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
mr: UD_Marathi-UFAL	raw	Tokens	not measured	100.00 [100.00, 100.00]	99.20 (Trankit large, UD 2.5; test same size) — within or ahead	97.99 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
mr: UD_Marathi-UFAL	raw	UAS	not measured	60.91 [51.46, 69.66]	72.79 (Trankit large, UD 2.5; test same size) — MISS	68.87 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
mr: UD_Marathi-UFAL	raw	UFeats	not measured	38.32 [33.85, 43.07]	74.45 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	73.53 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mr: UD_Marathi-UFAL	raw	UPOS	not measured	74.11 [69.57, 78.53]	87.79 (Trankit large, UD 2.5; test same size) — MISS	85.78 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mr: UD_Marathi-UFAL	raw	Words	not measured	86.29 [81.97, 90.71]	97.22 (Trankit large, UD 2.5; test same size) — MISS	92.89 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mt: UD_Maltese-MUDT	gold	AllTags	not measured	88.74 [88.04, 89.38]	95.43 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
mt: UD_Maltese-MUDT	gold	CLAS	not measured	71.21 [69.65, 72.69]	not published	not published
mt: UD_Maltese-MUDT	gold	LAS	not measured	78.33 [77.05, 79.52]	80.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
mt: UD_Maltese-MUDT	gold	MLAS	not measured	63.68 [62.10, 65.29]	68.61 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
mt: UD_Maltese-MUDT	gold	UAS	not measured	83.92 [82.73, 85.04]	85.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
mt: UD_Maltese-MUDT	gold	UFeats	not measured	100.00 [100.00, 100.00]	100.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
mt: UD_Maltese-MUDT	gold	UPOS	not measured	93.68 [93.10, 94.18]	95.88 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
mt: UD_Maltese-MUDT	gold	XPOS	not measured	90.00 [89.37, 90.64]	95.90 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
mt: UD_Maltese-MUDT	raw	AllTags	not measured	65.68 [64.63, 66.79]	95.35 (Stanza 1.5.1, UD 2.12; test same size) — MISS	95.35 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mt: UD_Maltese-MUDT	raw	CLAS	not measured	42.42 [40.64, 44.15]	70.76 (Stanza 1.5.1, UD 2.12; test same size) — MISS	70.76 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mt: UD_Maltese-MUDT	raw	LAS	not measured	45.83 [44.35, 47.41]	80.04 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	78.22 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mt: UD_Maltese-MUDT	raw	MLAS	not measured	35.62 [34.05, 37.16]	68.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	67.20 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mt: UD_Maltese-MUDT	raw	Sentences	not measured	64.56 [60.41, 69.05]	86.29 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	85.35 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mt: UD_Maltese-MUDT	raw	Tokens	not measured	74.36 [73.25, 75.49]	99.85 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.85 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mt: UD_Maltese-MUDT	raw	UAS	not measured	49.18 [47.60, 50.89]	84.86 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	83.62 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mt: UD_Maltese-MUDT	raw	UFeats	not measured	74.36 [73.25, 75.49]	99.85 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.85 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mt: UD_Maltese-MUDT	raw	UPOS	not measured	69.86 [68.71, 70.99]	95.78 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	95.72 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mt: UD_Maltese-MUDT	raw	Words	not measured	74.36 [73.25, 75.49]	99.85 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.85 (Stanza 1.5.1, UD 2.12; test same size) — MISS
mt: UD_Maltese-MUDT	raw	XPOS	not measured	66.72 [65.56, 67.86]	95.79 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	95.61 (Stanza 1.5.1, UD 2.12; test same size) — MISS
myv: UD_Erzya-JR	gold	AllTags	not measured	51.29 [50.32, 52.26]	74.86 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
myv: UD_Erzya-JR	gold	CLAS	not measured	40.87 [39.41, 42.54]	not published	not published
myv: UD_Erzya-JR	gold	LAS	not measured	47.25 [45.94, 48.65]	64.70 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
myv: UD_Erzya-JR	gold	Lemmas	not measured	70.08 [69.19, 70.92]	84.87 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
myv: UD_Erzya-JR	gold	MLAS	not measured	19.12 [18.03, 20.26]	42.76 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
myv: UD_Erzya-JR	gold	UAS	not measured	60.64 [59.17, 62.12]	74.25 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
myv: UD_Erzya-JR	gold	UFeats	not measured	57.01 [56.11, 57.93]	79.93 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
myv: UD_Erzya-JR	gold	UPOS	not measured	75.05 [74.17, 75.92]	89.25 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
myv: UD_Erzya-JR	gold	XPOS	not measured	76.79 [75.93, 77.59]	88.73 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
myv: UD_Erzya-JR	raw	AllTags	not measured	52.66 [51.72, 53.53]	74.38 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	69.52 (Stanza 1.5.1, UD 2.12; test changed) — MISS
myv: UD_Erzya-JR	raw	CLAS	not measured	47.96 [46.52, 49.39]	52.10 (Stanza 1.5.1, UD 2.12; test changed) — MISS	52.10 (Stanza 1.5.1, UD 2.12; test changed) — MISS
myv: UD_Erzya-JR	raw	LAS	not measured	54.23 [52.86, 55.57]	63.92 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	57.35 (Stanza 1.5.1, UD 2.12; test changed) — MISS
myv: UD_Erzya-JR	raw	Lemmas	not measured	71.48 [70.56, 72.36]	84.72 (Stanza 1.5.1, UD 2.12; test changed) — MISS	84.72 (Stanza 1.5.1, UD 2.12; test changed) — MISS
myv: UD_Erzya-JR	raw	MLAS	not measured	22.89 [21.77, 24.10]	42.32 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	36.09 (Stanza 1.5.1, UD 2.12; test changed) — MISS
myv: UD_Erzya-JR	raw	Sentences	not measured	88.78 [86.67, 90.57]	97.02 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	96.92 (Stanza 1.5.1, UD 2.12; test changed) — MISS
myv: UD_Erzya-JR	raw	Tokens	not measured	99.54 [99.36, 99.69]	99.63 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead	99.63 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
myv: UD_Erzya-JR	raw	UAS	not measured	68.25 [66.78, 69.66]	73.33 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	70.08 (Stanza 1.5.1, UD 2.12; test changed) — MISS
myv: UD_Erzya-JR	raw	UFeats	not measured	58.35 [57.40, 59.22]	79.36 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	75.88 (Stanza 1.5.1, UD 2.12; test changed) — MISS
myv: UD_Erzya-JR	raw	UPOS	not measured	76.37 [75.55, 77.17]	88.50 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	84.84 (Stanza 1.5.1, UD 2.12; test changed) — MISS
myv: UD_Erzya-JR	raw	Words	not measured	98.98 [98.69, 99.22]	99.12 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	99.08 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
myv: UD_Erzya-JR	raw	XPOS	not measured	78.29 [77.49, 79.07]	88.04 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	83.29 (Stanza 1.5.1, UD 2.12; test changed) — MISS
nds: UD_Low_Saxon-LSDC	gold	CLAS	not measured	53.25 [51.60, 54.90]	not published	not published
nds: UD_Low_Saxon-LSDC	gold	LAS	not measured	60.37 [58.92, 61.90]	65.93 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nds: UD_Low_Saxon-LSDC	gold	Lemmas	not measured	80.89 [79.99, 81.80]	84.33 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nds: UD_Low_Saxon-LSDC	gold	MLAS	not measured	24.10 [22.94, 25.34]	36.74 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nds: UD_Low_Saxon-LSDC	gold	UAS	not measured	69.57 [68.00, 71.18]	75.13 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nds: UD_Low_Saxon-LSDC	gold	UFeats	not measured	62.06 [61.10, 63.09]	72.23 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nds: UD_Low_Saxon-LSDC	gold	UPOS	not measured	83.92 [83.02, 84.85]	90.80 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nds: UD_Low_Saxon-LSDC	raw	CLAS	not measured	63.87 [62.41, 65.69]	not published	not published
nds: UD_Low_Saxon-LSDC	raw	LAS	not measured	69.59 [68.18, 71.11]	64.88 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
nds: UD_Low_Saxon-LSDC	raw	Lemmas	not measured	81.66 [80.81, 82.53]	83.84 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nds: UD_Low_Saxon-LSDC	raw	MLAS	not measured	30.05 [28.72, 31.52]	36.33 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nds: UD_Low_Saxon-LSDC	raw	Sentences	not measured	91.08 [88.59, 93.39]	90.23 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
nds: UD_Low_Saxon-LSDC	raw	Tokens	not measured	99.65 [99.48, 99.81]	not published	not published
nds: UD_Low_Saxon-LSDC	raw	UAS	not measured	77.79 [76.34, 79.26]	73.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
nds: UD_Low_Saxon-LSDC	raw	UFeats	not measured	62.89 [61.93, 63.94]	71.74 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nds: UD_Low_Saxon-LSDC	raw	UPOS	not measured	86.22 [85.42, 87.04]	90.25 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nds: UD_Low_Saxon-LSDC	raw	Words	not measured	99.41 [99.14, 99.65]	99.25 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
nl: UD_Dutch-Alpino	gold	AllTags	94.31 [93.48, 95.00]	94.13 [93.32, 94.87]	96.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nl: UD_Dutch-Alpino	gold	CLAS	not measured	82.88 [81.34, 84.21]	not published	not published
nl: UD_Dutch-Alpino	gold	LAS	87.63 [86.63, 88.59]	87.24 [86.15, 88.24]	93.37 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nl: UD_Dutch-Alpino	gold	Lemmas	91.88 [91.32, 92.47]	92.34 [91.80, 92.92]	96.20 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nl: UD_Dutch-Alpino	gold	MLAS	not measured	76.21 [74.34, 77.73]	86.35 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nl: UD_Dutch-Alpino	gold	UAS	90.41 [89.40, 91.32]	90.23 [89.24, 91.11]	95.30 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nl: UD_Dutch-Alpino	gold	UFeats	96.73 [96.16, 97.22]	96.62 [96.06, 97.12]	97.75 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nl: UD_Dutch-Alpino	gold	UPOS	96.89 [96.24, 97.44]	96.91 [96.21, 97.44]	98.17 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nl: UD_Dutch-Alpino	gold	XPOS	95.09 [94.32, 95.77]	95.05 [94.26, 95.72]	97.12 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
nl: UD_Dutch-Alpino	raw	AllTags	94.31 [93.58, 95.01]	94.50 [93.79, 95.22]	96.56 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.97 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
nl: UD_Dutch-Alpino	raw	CLAS	not measured	87.99 [86.70, 89.11]	89.56 (Trankit large, UD 2.5; test same size) — MISS	83.94 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
nl: UD_Dutch-Alpino	raw	LAS	89.06 [87.93, 89.96]	91.11 [90.20, 91.92]	92.49 (Trankit large, UD 2.5; test same size) — MISS	88.67 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
nl: UD_Dutch-Alpino	raw	Lemmas	91.54 [90.97, 92.14]	92.05 [91.49, 92.67]	96.39 (Trankit large, UD 2.5; test same size) — MISS	95.33 (Stanza 1.5.1, UD 2.12; test same size) — MISS
nl: UD_Dutch-Alpino	raw	MLAS	not measured	82.24 [80.73, 83.63]	85.14 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	79.65 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
nl: UD_Dutch-Alpino	raw	Sentences	94.81 [92.78, 96.42]	95.90 [94.35, 97.34]	91.16 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	90.08 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
nl: UD_Dutch-Alpino	raw	Tokens	99.66 [99.46, 99.82]	99.66 [99.46, 99.82]	99.87 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.87 (Stanza 1.5.1, UD 2.12; test same size) — MISS
nl: UD_Dutch-Alpino	raw	UAS	91.67 [90.65, 92.52]	93.37 [92.55, 94.08]	94.41 (Trankit large, UD 2.5; test same size) — MISS	91.42 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
nl: UD_Dutch-Alpino	raw	UFeats	96.78 [96.26, 97.27]	96.80 [96.29, 97.28]	97.52 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	97.00 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
nl: UD_Dutch-Alpino	raw	UPOS	96.66 [96.01, 97.23]	96.74 [96.11, 97.27]	97.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.75 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
nl: UD_Dutch-Alpino	raw	Words	99.66 [99.46, 99.82]	99.66 [99.46, 99.82]	99.87 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.87 (Stanza 1.5.1, UD 2.12; test same size) — MISS
nl: UD_Dutch-Alpino	raw	XPOS	95.03 [94.32, 95.67]	95.27 [94.61, 95.94]	96.89 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	95.50 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
no: UD_Norwegian-Bokmaal	gold	AllTags	not measured	79.66 [79.14, 80.14]	97.01 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
no: UD_Norwegian-Bokmaal	gold	CLAS	not measured	77.86 [77.09, 78.70]	not published	not published
no: UD_Norwegian-Bokmaal	gold	LAS	not measured	82.98 [82.32, 83.67]	93.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
no: UD_Norwegian-Bokmaal	gold	Lemmas	not measured	94.34 [94.06, 94.60]	98.87 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
no: UD_Norwegian-Bokmaal	gold	MLAS	not measured	54.53 [53.68, 55.36]	87.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
no: UD_Norwegian-Bokmaal	gold	UAS	not measured	86.61 [85.96, 87.26]	94.69 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
no: UD_Norwegian-Bokmaal	gold	UFeats	not measured	82.49 [82.00, 82.96]	97.59 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
no: UD_Norwegian-Bokmaal	gold	UPOS	not measured	95.93 [95.54, 96.29]	98.57 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
no: UD_Norwegian-Bokmaal	gold	XPOS	not measured	96.63 [96.25, 96.98]	99.17 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
no: UD_Norwegian-Bokmaal	raw	AllTags	not measured	79.29 [78.77, 79.79]	97.61 (Trankit large, UD 2.5; test same size) — MISS	96.38 (Stanza 1.5.1, UD 2.12; test same size) — MISS
no: UD_Norwegian-Bokmaal	raw	CLAS	not measured	85.08 [84.24, 85.81]	92.82 (Trankit large, UD 2.5; test same size) — MISS	89.11 (Stanza 1.5.1, UD 2.12; test same size) — MISS
no: UD_Norwegian-Bokmaal	raw	LAS	not measured	88.26 [87.58, 88.85]	94.33 (Trankit large, UD 2.5; test same size) — MISS	91.85 (Stanza 1.5.1, UD 2.12; test same size) — MISS
no: UD_Norwegian-Bokmaal	raw	Lemmas	not measured	93.79 [93.49, 94.10]	98.67 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	98.61 (Stanza 1.5.1, UD 2.12; test same size) — MISS
no: UD_Norwegian-Bokmaal	raw	MLAS	not measured	59.86 [58.97, 60.75]	90.15 (Trankit large, UD 2.5; test same size) — MISS	85.13 (Stanza 1.5.1, UD 2.12; test same size) — MISS
no: UD_Norwegian-Bokmaal	raw	Sentences	not measured	92.95 [91.84, 94.03]	99.20 (Trankit base, UD 2.5; test same size) — MISS	97.70 (Stanza 1.5.1, UD 2.12; test same size) — MISS
no: UD_Norwegian-Bokmaal	raw	Tokens	not measured	99.50 [99.38, 99.60]	99.88 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.88 (Stanza 1.5.1, UD 2.12; test same size) — MISS
no: UD_Norwegian-Bokmaal	raw	UAS	not measured	90.80 [90.15, 91.37]	95.54 (Trankit large, UD 2.5; test same size) — MISS	93.26 (Stanza 1.5.1, UD 2.12; test same size) — MISS
no: UD_Norwegian-Bokmaal	raw	UFeats	not measured	81.74 [81.25, 82.21]	98.07 (Trankit large, UD 2.5; test same size) — MISS	97.09 (Stanza 1.5.1, UD 2.12; test same size) — MISS
no: UD_Norwegian-Bokmaal	raw	UPOS	not measured	95.96 [95.58, 96.30]	98.85 (Trankit large, UD 2.5; test same size) — MISS	98.38 (Stanza 1.5.1, UD 2.12; test same size) — MISS
no: UD_Norwegian-Bokmaal	raw	Words	not measured	99.50 [99.38, 99.60]	99.88 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.88 (Stanza 1.5.1, UD 2.12; test same size) — MISS
no: UD_Norwegian-Bokmaal	raw	XPOS	not measured	96.89 [96.51, 97.22]	99.88 (Trankit large, UD 2.5; test same size) — MISS	99.04 (Stanza 1.5.1, UD 2.12; test same size) — MISS
olo: UD_Livvi-KKPP	gold	AllTags	not measured	3.83 [2.79, 4.84]	not published	not published
olo: UD_Livvi-KKPP	gold	CLAS	not measured	24.64 [21.78, 27.57]	not published	not published
olo: UD_Livvi-KKPP	gold	LAS	not measured	29.37 [26.68, 32.19]	not published	not published
olo: UD_Livvi-KKPP	gold	Lemmas	not measured	47.98 [45.38, 50.23]	not published	not published
olo: UD_Livvi-KKPP	gold	MLAS	not measured	1.41 [0.71, 2.23]	not published	not published
olo: UD_Livvi-KKPP	gold	UAS	not measured	48.05 [44.69, 51.76]	not published	not published
olo: UD_Livvi-KKPP	gold	UFeats	not measured	10.35 [8.70, 11.98]	not published	not published
olo: UD_Livvi-KKPP	gold	UPOS	not measured	36.96 [34.50, 39.59]	not published	not published
olo: UD_Livvi-KKPP	gold	XPOS	not measured	35.69 [32.79, 38.82]	not published	not published
olo: UD_Livvi-KKPP	raw	AllTags	not measured	10.52 [9.33, 11.82]	not published	not published
olo: UD_Livvi-KKPP	raw	CLAS	not measured	29.94 [26.69, 33.16]	not published	not published
olo: UD_Livvi-KKPP	raw	LAS	not measured	32.98 [29.67, 36.26]	not published	not published
olo: UD_Livvi-KKPP	raw	Lemmas	not measured	46.98 [44.31, 49.50]	not published	not published
olo: UD_Livvi-KKPP	raw	MLAS	not measured	1.92 [1.11, 2.81]	not published	not published
olo: UD_Livvi-KKPP	raw	Sentences	not measured	26.94 [19.19, 35.54]	not published	not published
olo: UD_Livvi-KKPP	raw	Tokens	not measured	98.86 [98.15, 99.49]	not published	not published
olo: UD_Livvi-KKPP	raw	UAS	not measured	51.34 [47.43, 55.19]	not published	not published
olo: UD_Livvi-KKPP	raw	UFeats	not measured	14.75 [13.25, 16.50]	not published	not published
olo: UD_Livvi-KKPP	raw	UPOS	not measured	44.37 [41.50, 47.23]	not published	not published
olo: UD_Livvi-KKPP	raw	Words	not measured	98.86 [98.15, 99.49]	not published	not published
olo: UD_Livvi-KKPP	raw	XPOS	not measured	42.23 [39.39, 45.42]	not published	not published
orv: UD_Old_East_Slavic-RNC	gold	AllTags	not measured	0.18 [0.13, 0.23]	82.65 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
orv: UD_Old_East_Slavic-RNC	gold	CLAS	not measured	59.04 [57.82, 60.34]	not published	not published
orv: UD_Old_East_Slavic-RNC	gold	LAS	not measured	66.62 [65.53, 67.76]	78.58 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
orv: UD_Old_East_Slavic-RNC	gold	Lemmas	not measured	79.36 [78.68, 80.01]	90.81 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
orv: UD_Old_East_Slavic-RNC	gold	MLAS	not measured	25.71 [24.47, 26.88]	60.21 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
orv: UD_Old_East_Slavic-RNC	gold	UAS	not measured	71.64 [70.28, 72.92]	82.12 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
orv: UD_Old_East_Slavic-RNC	gold	UFeats	not measured	64.39 [63.59, 65.16]	90.38 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
orv: UD_Old_East_Slavic-RNC	gold	UPOS	not measured	90.98 [90.54, 91.45]	98.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
orv: UD_Old_East_Slavic-RNC	gold	XPOS	not measured	0.77 [0.61, 0.96]	91.56 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
orv: UD_Old_East_Slavic-RNC	raw	AllTags	not measured	0.18 [0.13, 0.23]	82.43 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	64.40 (Stanza 1.5.1, UD 2.12; test changed) — MISS
orv: UD_Old_East_Slavic-RNC	raw	CLAS	not measured	58.45 [56.77, 60.09]	51.90 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead	51.90 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
orv: UD_Old_East_Slavic-RNC	raw	LAS	not measured	65.14 [63.69, 66.63]	77.10 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	60.81 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
orv: UD_Old_East_Slavic-RNC	raw	Lemmas	not measured	76.43 [75.40, 77.44]	90.60 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	81.04 (Stanza 1.5.1, UD 2.12; test changed) — MISS
orv: UD_Old_East_Slavic-RNC	raw	MLAS	not measured	26.36 [25.18, 27.55]	58.83 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	33.25 (Stanza 1.5.1, UD 2.12; test changed) — MISS
orv: UD_Old_East_Slavic-RNC	raw	Sentences	not measured	77.71 [74.93, 80.37]	94.56 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	89.29 (Stanza 1.5.1, UD 2.12; test changed) — MISS
orv: UD_Old_East_Slavic-RNC	raw	Tokens	not measured	94.29 [93.17, 95.25]	99.14 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.14 (Stanza 1.5.1, UD 2.12; test changed) — MISS
orv: UD_Old_East_Slavic-RNC	raw	UAS	not measured	69.06 [67.51, 70.59]	80.58 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	68.10 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
orv: UD_Old_East_Slavic-RNC	raw	UFeats	not measured	62.63 [61.64, 63.62]	90.13 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	72.39 (Stanza 1.5.1, UD 2.12; test changed) — MISS
orv: UD_Old_East_Slavic-RNC	raw	UPOS	not measured	87.23 [86.10, 88.24]	97.77 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	91.04 (Stanza 1.5.1, UD 2.12; test changed) — MISS
orv: UD_Old_East_Slavic-RNC	raw	Words	not measured	94.29 [93.17, 95.25]	99.77 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.14 (Stanza 1.5.1, UD 2.12; test changed) — MISS
orv: UD_Old_East_Slavic-RNC	raw	XPOS	not measured	0.74 [0.59, 0.92]	91.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	87.53 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ota: UD_Ottoman_Turkish-BOUN	gold	AllTags	not measured	22.38 [21.42, 23.47]	71.24 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ota: UD_Ottoman_Turkish-BOUN	gold	CLAS	not measured	49.18 [47.57, 51.01]	not published	not published
ota: UD_Ottoman_Turkish-BOUN	gold	LAS	not measured	53.30 [51.69, 55.05]	53.06 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
ota: UD_Ottoman_Turkish-BOUN	gold	Lemmas	not measured	71.93 [70.73, 73.16]	82.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ota: UD_Ottoman_Turkish-BOUN	gold	MLAS	not measured	24.74 [23.36, 26.21]	33.26 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ota: UD_Ottoman_Turkish-BOUN	gold	UAS	not measured	63.25 [61.59, 65.00]	64.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
ota: UD_Ottoman_Turkish-BOUN	gold	UFeats	not measured	65.77 [64.62, 66.99]	80.96 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ota: UD_Ottoman_Turkish-BOUN	gold	UPOS	not measured	87.06 [86.18, 87.91]	86.18 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
ota: UD_Ottoman_Turkish-BOUN	gold	XPOS	not measured	36.50 [35.42, 37.62]	90.81 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ota: UD_Ottoman_Turkish-BOUN	raw	AllTags	not measured	22.74 [21.81, 23.78]	70.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ota: UD_Ottoman_Turkish-BOUN	raw	CLAS	not measured	56.78 [55.03, 58.62]	not published	not published
ota: UD_Ottoman_Turkish-BOUN	raw	LAS	not measured	60.16 [58.55, 61.82]	52.37 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
ota: UD_Ottoman_Turkish-BOUN	raw	Lemmas	not measured	71.73 [70.53, 72.92]	81.99 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ota: UD_Ottoman_Turkish-BOUN	raw	MLAS	not measured	29.74 [28.17, 31.21]	32.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ota: UD_Ottoman_Turkish-BOUN	raw	Sentences	not measured	86.01 [82.52, 89.41]	87.39 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
ota: UD_Ottoman_Turkish-BOUN	raw	Tokens	not measured	99.52 [99.24, 99.77]	not published	not published
ota: UD_Ottoman_Turkish-BOUN	raw	UAS	not measured	70.12 [68.62, 71.73]	63.60 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
ota: UD_Ottoman_Turkish-BOUN	raw	UFeats	not measured	68.04 [66.90, 69.24]	80.51 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ota: UD_Ottoman_Turkish-BOUN	raw	UPOS	not measured	86.51 [85.54, 87.45]	85.77 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
ota: UD_Ottoman_Turkish-BOUN	raw	Words	not measured	99.32 [99.02, 99.61]	99.44 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
ota: UD_Ottoman_Turkish-BOUN	raw	XPOS	not measured	36.82 [35.72, 37.92]	90.42 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pa: UD_Punjabi-Rang	gold	CLAS	not measured	45.92 [39.05, 53.05]	not published	not published
pa: UD_Punjabi-Rang	gold	LAS	not measured	49.00 [42.61, 55.25]	not published	not published
pa: UD_Punjabi-Rang	gold	Lemmas	not measured	79.00 [74.77, 82.86]	not published	not published
pa: UD_Punjabi-Rang	gold	MLAS	not measured	12.24 [8.85, 16.26]	not published	not published
pa: UD_Punjabi-Rang	gold	UAS	not measured	66.33 [60.36, 72.85]	not published	not published
pa: UD_Punjabi-Rang	gold	UFeats	not measured	58.33 [53.18, 62.91]	not published	not published
pa: UD_Punjabi-Rang	gold	UPOS	not measured	74.33 [69.86, 79.44]	not published	not published
pa: UD_Punjabi-Rang	raw	CLAS	not measured	43.55 [36.02, 51.61]	not published	not published
pa: UD_Punjabi-Rang	raw	LAS	not measured	47.67 [41.55, 54.04]	not published	not published
pa: UD_Punjabi-Rang	raw	Lemmas	not measured	79.00 [74.52, 82.86]	not published	not published
pa: UD_Punjabi-Rang	raw	MLAS	not measured	10.75 [5.78, 16.62]	not published	not published
pa: UD_Punjabi-Rang	raw	Sentences	not measured	48.78 [28.57, 68.29]	not published	not published
pa: UD_Punjabi-Rang	raw	Tokens	not measured	100.00 [100.00, 100.00]	not published	not published
pa: UD_Punjabi-Rang	raw	UAS	not measured	62.33 [54.87, 69.20]	not published	not published
pa: UD_Punjabi-Rang	raw	UFeats	not measured	61.67 [57.29, 66.08]	not published	not published
pa: UD_Punjabi-Rang	raw	UPOS	not measured	71.33 [66.67, 75.68]	not published	not published
pa: UD_Punjabi-Rang	raw	Words	not measured	100.00 [100.00, 100.00]	not published	not published
pcm: UD_Naija-NSC	gold	CLAS	not measured	72.92 [71.48, 74.35]	not published	not published
pcm: UD_Naija-NSC	gold	LAS	not measured	77.80 [76.59, 79.04]	90.03 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pcm: UD_Naija-NSC	gold	Lemmas	not measured	98.18 [97.90, 98.45]	99.31 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pcm: UD_Naija-NSC	gold	MLAS	not measured	62.01 [60.37, 63.61]	84.13 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pcm: UD_Naija-NSC	gold	UAS	not measured	83.76 [82.61, 84.95]	92.68 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pcm: UD_Naija-NSC	gold	UFeats	not measured	94.78 [94.33, 95.23]	98.93 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pcm: UD_Naija-NSC	gold	UPOS	not measured	93.41 [92.94, 93.86]	98.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pcm: UD_Naija-NSC	raw	CLAS	not measured	70.47 [68.80, 71.95]	88.60 (Stanza 1.5.1, UD 2.12; test same size) — MISS	88.60 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pcm: UD_Naija-NSC	raw	LAS	not measured	70.52 [69.09, 71.90]	89.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	89.56 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pcm: UD_Naija-NSC	raw	Lemmas	not measured	91.69 [91.06, 92.29]	99.28 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.14 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pcm: UD_Naija-NSC	raw	MLAS	not measured	59.40 [57.82, 60.86]	86.43 (Stanza 1.5.1, UD 2.12; test same size) — MISS	86.43 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pcm: UD_Naija-NSC	raw	Sentences	not measured	79.29 [76.93, 81.60]	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS	100.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pcm: UD_Naija-NSC	raw	Tokens	not measured	92.84 [92.26, 93.41]	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pcm: UD_Naija-NSC	raw	UAS	not measured	75.89 [74.49, 77.33]	92.62 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	92.39 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pcm: UD_Naija-NSC	raw	UFeats	not measured	87.98 [87.21, 88.74]	98.90 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	98.84 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pcm: UD_Naija-NSC	raw	UPOS	not measured	87.23 [86.44, 88.00]	98.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	97.55 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pcm: UD_Naija-NSC	raw	Words	not measured	92.84 [92.26, 93.41]	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pl: UD_Polish-MPDT	gold	AllTags	not measured	58.11 [57.06, 59.12]	88.01 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	gold	CLAS	not measured	59.62 [57.97, 61.33]	not published	not published
pl: UD_Polish-MPDT	gold	LAS	not measured	65.29 [63.82, 66.70]	78.54 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	gold	Lemmas	not measured	84.84 [84.10, 85.62]	96.35 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	gold	MLAS	not measured	29.31 [27.92, 30.67]	63.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	gold	UAS	not measured	72.40 [70.93, 73.72]	82.66 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	gold	UFeats	not measured	68.09 [67.09, 69.07]	91.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	gold	UPOS	not measured	87.29 [86.49, 88.03]	96.29 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	gold	XPOS	not measured	66.19 [65.19, 67.25]	90.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	raw	AllTags	not measured	59.11 [58.14, 60.11]	86.51 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	raw	CLAS	not measured	63.52 [61.84, 65.04]	not published	not published
pl: UD_Polish-MPDT	raw	LAS	not measured	67.83 [66.27, 69.25]	75.06 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	raw	Lemmas	not measured	83.03 [82.17, 83.94]	94.70 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	raw	MLAS	not measured	31.42 [30.02, 32.70]	60.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	raw	Sentences	not measured	75.73 [71.70, 79.64]	87.46 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	raw	Tokens	not measured	98.93 [98.65, 99.20]	not published	not published
pl: UD_Polish-MPDT	raw	UAS	not measured	73.27 [71.78, 74.66]	78.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	raw	UFeats	not measured	68.13 [67.15, 69.12]	89.44 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	raw	UPOS	not measured	86.08 [85.21, 86.88]	94.59 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	raw	Words	not measured	96.80 [96.29, 97.28]	98.22 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pl: UD_Polish-MPDT	raw	XPOS	not measured	66.98 [66.01, 68.05]	88.43 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pro: UD_Old_Occitan-CorAG	gold	CLAS	not measured	58.36 [56.05, 60.78]	not published	not published
pro: UD_Old_Occitan-CorAG	gold	LAS	not measured	66.97 [64.71, 69.20]	80.85 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pro: UD_Old_Occitan-CorAG	gold	MLAS	not measured	42.81 [40.62, 44.80]	69.04 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pro: UD_Old_Occitan-CorAG	gold	UAS	not measured	72.61 [70.28, 74.89]	83.90 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pro: UD_Old_Occitan-CorAG	gold	UFeats	not measured	88.11 [87.08, 89.06]	97.02 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pro: UD_Old_Occitan-CorAG	gold	UPOS	not measured	88.64 [87.74, 89.47]	96.83 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pro: UD_Old_Occitan-CorAG	raw	CLAS	not measured	57.05 [54.28, 59.82]	not published	not published
pro: UD_Old_Occitan-CorAG	raw	LAS	not measured	62.08 [59.46, 64.73]	74.80 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pro: UD_Old_Occitan-CorAG	raw	MLAS	not measured	40.76 [38.51, 43.02]	63.84 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pro: UD_Old_Occitan-CorAG	raw	Sentences	not measured	57.74 [51.69, 63.62]	83.64 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pro: UD_Old_Occitan-CorAG	raw	Tokens	not measured	95.35 [94.57, 96.17]	not published	not published
pro: UD_Old_Occitan-CorAG	raw	UAS	not measured	66.36 [63.69, 69.18]	77.79 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pro: UD_Old_Occitan-CorAG	raw	UFeats	not measured	80.84 [79.60, 82.01]	95.37 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pro: UD_Old_Occitan-CorAG	raw	UPOS	not measured	82.51 [81.42, 83.58]	95.25 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pro: UD_Old_Occitan-CorAG	raw	Words	not measured	91.16 [90.34, 91.98]	98.55 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
pt: UD_Portuguese-Bosque	gold	CLAS	not measured	80.24 [79.51, 81.07]	not published	not published
pt: UD_Portuguese-Bosque	gold	LAS	84.01 [83.39, 84.63]	84.54 [83.90, 85.14]	90.93 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pt: UD_Portuguese-Bosque	gold	Lemmas	97.49 [97.30, 97.70]	97.59 [97.39, 97.79]	98.63 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pt: UD_Portuguese-Bosque	gold	MLAS	not measured	70.29 [69.36, 71.22]	81.55 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pt: UD_Portuguese-Bosque	gold	UAS	87.64 [87.07, 88.25]	88.22 [87.63, 88.77]	93.31 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pt: UD_Portuguese-Bosque	gold	UFeats	94.80 [94.49, 95.09]	94.48 [94.16, 94.80]	97.15 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pt: UD_Portuguese-Bosque	gold	UPOS	96.56 [96.32, 96.80]	96.10 [95.82, 96.36]	98.09 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
pt: UD_Portuguese-Bosque	raw	CLAS	not measured	85.27 [84.54, 85.99]	87.75 (Trankit large, UD 2.5; test changed) — MISS	82.66 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
pt: UD_Portuguese-Bosque	raw	LAS	86.47 [85.84, 87.04]	87.98 [87.39, 88.55]	90.91 (Trankit large, UD 2.5; test changed) — MISS	87.75 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
pt: UD_Portuguese-Bosque	raw	Lemmas	96.96 [96.73, 97.19]	97.29 [97.09, 97.50]	98.33 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	98.04 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pt: UD_Portuguese-Bosque	raw	MLAS	not measured	76.55 [75.69, 77.41]	81.09 (Trankit large, UD 2.5; test changed) — MISS	77.07 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
pt: UD_Portuguese-Bosque	raw	Sentences	92.27 [90.68, 93.82]	93.50 [92.14, 94.81]	97.48 (Trankit base, UD 2.5; test changed) — MISS	93.10 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
pt: UD_Portuguese-Bosque	raw	Tokens	99.86 [99.79, 99.92]	99.86 [99.79, 99.92]	99.85 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	99.85 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
pt: UD_Portuguese-Bosque	raw	UAS	89.38 [88.77, 89.91]	90.68 [90.16, 91.19]	93.31 (Trankit large, UD 2.5; test changed) — MISS	90.59 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
pt: UD_Portuguese-Bosque	raw	UFeats	95.06 [94.75, 95.34]	95.19 [94.90, 95.48]	96.89 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.44 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pt: UD_Portuguese-Bosque	raw	UPOS	96.59 [96.32, 96.83]	96.75 [96.50, 96.98]	97.77 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	97.45 (Stanza 1.5.1, UD 2.12; test same size) — MISS
pt: UD_Portuguese-Bosque	raw	Words	99.26 [99.14, 99.38]	99.26 [99.14, 99.38]	99.76 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.76 (Stanza 1.5.1, UD 2.12; test same size) — MISS
qte: UD_Telugu_English-TECT	gold	AllTags	not measured	67.47 [60.24, 74.85]	not published	not published
qte: UD_Telugu_English-TECT	gold	CLAS	not measured	64.31 [55.17, 73.90]	not published	not published
qte: UD_Telugu_English-TECT	gold	LAS	not measured	68.67 [61.11, 76.54]	not published	not published
qte: UD_Telugu_English-TECT	gold	MLAS	not measured	37.65 [29.43, 46.81]	not published	not published
qte: UD_Telugu_English-TECT	gold	UAS	not measured	86.14 [79.29, 92.36]	not published	not published
qte: UD_Telugu_English-TECT	gold	UFeats	not measured	99.40 [98.18, 100.00]	not published	not published
qte: UD_Telugu_English-TECT	gold	UPOS	not measured	68.07 [61.08, 75.00]	not published	not published
qte: UD_Telugu_English-TECT	gold	XPOS	not measured	68.07 [60.95, 75.61]	not published	not published
qte: UD_Telugu_English-TECT	raw	AllTags	not measured	80.12 [72.88, 87.72]	not published	not published
qte: UD_Telugu_English-TECT	raw	CLAS	not measured	62.90 [51.38, 73.90]	not published	not published
qte: UD_Telugu_English-TECT	raw	LAS	not measured	69.88 [60.00, 79.53]	not published	not published
qte: UD_Telugu_English-TECT	raw	MLAS	not measured	55.65 [44.44, 67.78]	not published	not published
qte: UD_Telugu_English-TECT	raw	Sentences	not measured	83.58 [71.64, 94.12]	not published	not published
qte: UD_Telugu_English-TECT	raw	Tokens	not measured	100.00 [100.00, 100.00]	not published	not published
qte: UD_Telugu_English-TECT	raw	UAS	not measured	85.54 [76.79, 92.99]	not published	not published
qte: UD_Telugu_English-TECT	raw	UFeats	not measured	99.40 [98.18, 100.00]	not published	not published
qte: UD_Telugu_English-TECT	raw	UPOS	not measured	80.72 [73.84, 87.80]	not published	not published
qte: UD_Telugu_English-TECT	raw	Words	not measured	100.00 [100.00, 100.00]	not published	not published
qte: UD_Telugu_English-TECT	raw	XPOS	not measured	80.12 [72.88, 87.72]	not published	not published
ro: UD_Romanian-RRT	gold	AllTags	not measured	73.10 [72.40, 73.85]	97.19 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
ro: UD_Romanian-RRT	gold	CLAS	not measured	76.60 [75.57, 77.61]	not published	not published
ro: UD_Romanian-RRT	gold	LAS	not measured	80.28 [79.46, 81.10]	89.53 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
ro: UD_Romanian-RRT	gold	Lemmas	not measured	94.09 [93.64, 94.54]	98.36 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
ro: UD_Romanian-RRT	gold	MLAS	not measured	48.34 [47.20, 49.55]	82.89 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
ro: UD_Romanian-RRT	gold	UAS	not measured	85.60 [84.82, 86.33]	92.77 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
ro: UD_Romanian-RRT	gold	UFeats	not measured	78.09 [77.38, 78.83]	97.64 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
ro: UD_Romanian-RRT	gold	UPOS	not measured	93.35 [92.92, 93.78]	98.14 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
ro: UD_Romanian-RRT	gold	XPOS	not measured	83.58 [82.95, 84.21]	97.48 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
ro: UD_Romanian-RRT	raw	AllTags	not measured	78.66 [77.97, 79.39]	97.11 (Trankit large, UD 2.5; test changed) — MISS	96.74 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ro: UD_Romanian-RRT	raw	CLAS	not measured	79.77 [78.67, 80.94]	86.61 (Trankit large, UD 2.5; test changed) — MISS	82.99 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ro: UD_Romanian-RRT	raw	LAS	not measured	82.32 [81.33, 83.35]	89.50 (Trankit large, UD 2.5; test changed) — MISS	86.86 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ro: UD_Romanian-RRT	raw	Lemmas	not measured	92.22 [91.71, 92.76]	98.10 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	97.42 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ro: UD_Romanian-RRT	raw	MLAS	not measured	57.93 [56.55, 59.29]	82.78 (Trankit large, UD 2.5; test changed) — MISS	79.90 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ro: UD_Romanian-RRT	raw	Sentences	not measured	89.05 [86.86, 91.15]	98.49 (Trankit large, UD 2.5; test changed) — MISS	95.72 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ro: UD_Romanian-RRT	raw	Tokens	not measured	96.96 [96.60, 97.31]	99.73 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.73 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ro: UD_Romanian-RRT	raw	UAS	not measured	86.02 [85.08, 86.94]	93.60 (Trankit large, UD 2.5; test changed) — MISS	90.70 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ro: UD_Romanian-RRT	raw	UFeats	not measured	81.68 [81.06, 82.39]	97.44 (Trankit base, UD 2.5; test changed) — MISS	97.10 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ro: UD_Romanian-RRT	raw	UPOS	not measured	91.67 [91.16, 92.16]	97.90 (Trankit large, UD 2.5; test changed) — MISS	97.50 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ro: UD_Romanian-RRT	raw	Words	not measured	96.96 [96.60, 97.31]	99.73 (Stanza 1.5.1, UD 2.12; test changed) — MISS	99.73 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ro: UD_Romanian-RRT	raw	XPOS	not measured	85.00 [84.38, 85.66]	97.35 (Trankit large, UD 2.5; test changed) — MISS	96.80 (Stanza 1.5.1, UD 2.12; test changed) — MISS
ru: UD_Russian-GSD	gold	AllTags	not measured	66.51 [65.46, 67.52]	92.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ru: UD_Russian-GSD	gold	CLAS	not measured	73.03 [70.98, 74.74]	not published	not published
ru: UD_Russian-GSD	gold	LAS	not measured	75.27 [72.81, 77.18]	90.19 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ru: UD_Russian-GSD	gold	Lemmas	not measured	87.93 [87.13, 88.70]	97.58 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ru: UD_Russian-GSD	gold	MLAS	not measured	41.80 [40.05, 43.56]	81.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ru: UD_Russian-GSD	gold	UAS	not measured	80.60 [78.19, 82.47]	93.25 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ru: UD_Russian-GSD	gold	UFeats	not measured	70.83 [69.82, 71.76]	94.18 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ru: UD_Russian-GSD	gold	UPOS	not measured	91.68 [91.13, 92.27]	98.54 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ru: UD_Russian-GSD	gold	XPOS	not measured	92.12 [91.33, 92.87]	97.87 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ru: UD_Russian-GSD	raw	AllTags	not measured	65.75 [63.92, 67.53]	94.73 (Trankit large, UD 2.5; test same size) — MISS	92.76 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ru: UD_Russian-GSD	raw	CLAS	not measured	82.94 [80.87, 84.72]	88.71 (Trankit large, UD 2.5; test same size) — MISS	83.91 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
ru: UD_Russian-GSD	raw	LAS	not measured	78.76 [75.58, 81.39]	89.75 (Trankit large, UD 2.5; test same size) — MISS	85.89 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ru: UD_Russian-GSD	raw	Lemmas	not measured	83.84 [81.63, 85.79]	97.20 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	95.51 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ru: UD_Russian-GSD	raw	MLAS	not measured	51.94 [49.99, 53.69]	82.92 (Trankit large, UD 2.5; test same size) — MISS	77.00 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ru: UD_Russian-GSD	raw	Sentences	not measured	92.26 [90.07, 94.24]	99.25 (Trankit large, UD 2.5; test same size) — MISS	97.33 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ru: UD_Russian-GSD	raw	Tokens	not measured	92.86 [90.99, 94.49]	99.79 (Trankit large, UD 2.5; test same size) — MISS	99.58 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ru: UD_Russian-GSD	raw	UAS	not measured	82.15 [78.95, 84.74]	92.70 (Trankit large, UD 2.5; test same size) — MISS	89.56 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ru: UD_Russian-GSD	raw	UFeats	not measured	69.12 [67.53, 70.70]	95.78 (Trankit large, UD 2.5; test same size) — MISS	93.63 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ru: UD_Russian-GSD	raw	UPOS	not measured	86.36 [84.48, 88.05]	98.25 (Trankit large, UD 2.5; test same size) — MISS	97.63 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ru: UD_Russian-GSD	raw	Words	not measured	92.86 [90.99, 94.49]	99.79 (Trankit large, UD 2.5; test same size) — MISS	99.58 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ru: UD_Russian-GSD	raw	XPOS	not measured	87.73 [85.60, 89.58]	97.89 (Trankit large, UD 2.5; test same size) — MISS	97.41 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sa: UD_Sanskrit-Vedic	gold	CLAS	not measured	32.81 [31.76, 33.95]	not published	not published
sa: UD_Sanskrit-Vedic	gold	LAS	not measured	34.05 [33.06, 35.15]	68.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sa: UD_Sanskrit-Vedic	gold	Lemmas	not measured	75.77 [75.04, 76.50]	93.50 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sa: UD_Sanskrit-Vedic	gold	MLAS	not measured	17.76 [17.00, 18.55]	60.40 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sa: UD_Sanskrit-Vedic	gold	UAS	not measured	50.53 [49.31, 51.78]	77.99 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sa: UD_Sanskrit-Vedic	gold	UFeats	not measured	51.29 [50.48, 52.14]	90.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sa: UD_Sanskrit-Vedic	gold	UPOS	not measured	70.59 [69.80, 71.37]	93.83 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sa: UD_Sanskrit-Vedic	raw	CLAS	not measured	19.56 [18.68, 20.43]	49.90 (Stanza 1.5.1, UD 2.12; test changed) — MISS	49.90 (Stanza 1.5.1, UD 2.12; test changed) — MISS
sa: UD_Sanskrit-Vedic	raw	LAS	not measured	21.48 [20.62, 22.37]	56.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	50.64 (Stanza 1.5.1, UD 2.12; test changed) — MISS
sa: UD_Sanskrit-Vedic	raw	Lemmas	not measured	75.57 [74.82, 76.32]	93.45 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	88.92 (Stanza 1.5.1, UD 2.12; test changed) — MISS
sa: UD_Sanskrit-Vedic	raw	MLAS	not measured	11.55 [10.94, 12.20]	49.07 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	43.27 (Stanza 1.5.1, UD 2.12; test changed) — MISS
sa: UD_Sanskrit-Vedic	raw	Sentences	not measured	7.22 [6.04, 8.52]	32.93 (Stanza 1.5.1, UD 2.12; test changed) — MISS	32.93 (Stanza 1.5.1, UD 2.12; test changed) — MISS
sa: UD_Sanskrit-Vedic	raw	Tokens	not measured	100.00 [100.00, 100.00]	100.00 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead	100.00 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
sa: UD_Sanskrit-Vedic	raw	UAS	not measured	32.91 [31.88, 33.99]	65.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	62.52 (Stanza 1.5.1, UD 2.12; test changed) — MISS
sa: UD_Sanskrit-Vedic	raw	UFeats	not measured	51.03 [50.19, 51.82]	89.24 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	80.70 (Stanza 1.5.1, UD 2.12; test changed) — MISS
sa: UD_Sanskrit-Vedic	raw	UPOS	not measured	70.54 [69.75, 71.32]	93.56 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	89.19 (Stanza 1.5.1, UD 2.12; test changed) — MISS
sa: UD_Sanskrit-Vedic	raw	Words	not measured	100.00 [100.00, 100.00]	100.00 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead	100.00 (Stanza 1.5.1, UD 2.12; test changed) — within or ahead
say: UD_Zaar-Autogramm	gold	CLAS	not measured	37.35 [35.92, 38.67]	not published	not published
say: UD_Zaar-Autogramm	gold	LAS	not measured	49.53 [48.16, 50.82]	73.34 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	gold	Lemmas	not measured	76.93 [76.12, 77.76]	87.42 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	gold	MLAS	not measured	17.13 [16.12, 18.16]	53.71 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	gold	UAS	not measured	67.81 [66.22, 69.22]	83.04 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	gold	UFeats	not measured	75.96 [75.11, 76.84]	91.37 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	gold	UPOS	not measured	66.51 [65.55, 67.43]	90.67 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	raw	CLAS	not measured	24.67 [23.21, 26.09]	not published	not published
say: UD_Zaar-Autogramm	raw	LAS	not measured	36.26 [34.74, 37.74]	62.81 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	raw	Lemmas	not measured	68.34 [67.29, 69.42]	82.47 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	raw	MLAS	not measured	12.24 [11.27, 13.22]	43.14 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	raw	Sentences	not measured	63.56 [60.64, 66.19]	98.93 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	raw	Tokens	not measured	97.49 [97.07, 97.92]	not published	not published
say: UD_Zaar-Autogramm	raw	UAS	not measured	49.09 [47.38, 50.77]	70.99 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	raw	UFeats	not measured	66.79 [65.80, 67.82]	85.78 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	raw	UPOS	not measured	62.38 [61.35, 63.50]	84.94 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
say: UD_Zaar-Autogramm	raw	Words	not measured	87.48 [86.71, 88.26]	94.06 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
sd: UD_Sindhi-Isra	gold	AllTags	not measured	54.53 [53.45, 55.53]	69.11 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	gold	CLAS	not measured	62.26 [60.63, 63.73]	not published	not published
sd: UD_Sindhi-Isra	gold	LAS	not measured	68.88 [67.40, 70.23]	76.42 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	gold	Lemmas	not measured	95.63 [95.19, 96.02]	94.88 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sd: UD_Sindhi-Isra	gold	MLAS	not measured	25.46 [24.16, 26.65]	41.22 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	gold	UAS	not measured	79.54 [78.22, 80.86]	85.51 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	gold	UFeats	not measured	58.35 [57.29, 59.41]	71.23 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	gold	UPOS	not measured	88.18 [87.42, 88.98]	93.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	gold	XPOS	not measured	87.16 [86.35, 87.93]	91.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	raw	AllTags	not measured	56.13 [55.01, 57.17]	68.89 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	raw	CLAS	not measured	61.01 [59.53, 62.49]	not published	not published
sd: UD_Sindhi-Isra	raw	LAS	not measured	68.19 [66.86, 69.52]	74.44 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	raw	Lemmas	not measured	95.89 [95.44, 96.28]	94.79 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sd: UD_Sindhi-Isra	raw	MLAS	not measured	27.07 [25.83, 28.33]	39.66 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	raw	Sentences	not measured	71.46 [68.49, 74.43]	88.28 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	raw	Tokens	not measured	99.99 [99.96, 100.00]	not published	not published
sd: UD_Sindhi-Isra	raw	UAS	not measured	78.38 [77.10, 79.68]	83.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	raw	UFeats	not measured	60.15 [59.02, 61.21]	71.01 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	raw	UPOS	not measured	88.87 [88.14, 89.57]	93.27 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sd: UD_Sindhi-Isra	raw	Words	not measured	99.99 [99.96, 100.00]	99.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sd: UD_Sindhi-Isra	raw	XPOS	not measured	87.00 [86.22, 87.72]	91.83 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sdh: UD_Southern_Kurdish-Garrusi	gold	CLAS	not measured	48.57 [38.78, 58.56]	not published	not published
sdh: UD_Southern_Kurdish-Garrusi	gold	LAS	not measured	54.41 [43.84, 65.00]	68.38 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sdh: UD_Southern_Kurdish-Garrusi	gold	Lemmas	not measured	59.56 [51.64, 66.43]	75.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sdh: UD_Southern_Kurdish-Garrusi	gold	MLAS	not measured	23.81 [16.41, 32.22]	45.63 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sdh: UD_Southern_Kurdish-Garrusi	gold	UAS	not measured	72.79 [60.51, 84.80]	76.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sdh: UD_Southern_Kurdish-Garrusi	gold	UFeats	not measured	61.03 [54.17, 69.05]	78.68 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sdh: UD_Southern_Kurdish-Garrusi	gold	UPOS	not measured	62.50 [55.40, 70.97]	83.82 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sdh: UD_Southern_Kurdish-Garrusi	raw	CLAS	not measured	59.70 [49.09, 73.26]	not published	not published
sdh: UD_Southern_Kurdish-Garrusi	raw	LAS	not measured	63.43 [52.99, 76.52]	62.09 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sdh: UD_Southern_Kurdish-Garrusi	raw	Lemmas	not measured	58.96 [50.22, 65.49]	67.15 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sdh: UD_Southern_Kurdish-Garrusi	raw	MLAS	not measured	46.77 [37.17, 58.76]	40.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sdh: UD_Southern_Kurdish-Garrusi	raw	Sentences	not measured	100.00 [100.00, 100.00]	92.68 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sdh: UD_Southern_Kurdish-Garrusi	raw	Tokens	not measured	100.00 [100.00, 100.00]	not published	not published
sdh: UD_Southern_Kurdish-Garrusi	raw	UAS	not measured	72.39 [61.09, 83.40]	68.59 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sdh: UD_Southern_Kurdish-Garrusi	raw	UFeats	not measured	72.39 [64.79, 81.27]	72.92 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sdh: UD_Southern_Kurdish-Garrusi	raw	UPOS	not measured	74.63 [68.10, 83.33]	77.26 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sdh: UD_Southern_Kurdish-Garrusi	raw	Words	not measured	95.52 [90.99, 98.92]	90.25 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sk: UD_Slovak-SNK	gold	AllTags	not measured	62.68 [61.73, 63.55]	89.19 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sk: UD_Slovak-SNK	gold	CLAS	not measured	77.40 [76.24, 78.53]	not published	not published
sk: UD_Slovak-SNK	gold	LAS	not measured	80.00 [79.04, 80.95]	91.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sk: UD_Slovak-SNK	gold	Lemmas	not measured	87.30 [86.65, 87.95]	96.66 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sk: UD_Slovak-SNK	gold	MLAS	not measured	45.69 [44.38, 46.86]	81.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sk: UD_Slovak-SNK	gold	UAS	not measured	84.02 [83.09, 84.86]	93.75 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sk: UD_Slovak-SNK	gold	UFeats	not measured	70.16 [69.26, 71.01]	93.31 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sk: UD_Slovak-SNK	gold	UPOS	not measured	91.25 [90.73, 91.76]	97.83 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sk: UD_Slovak-SNK	gold	XPOS	not measured	67.51 [66.60, 68.37]	90.18 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sk: UD_Slovak-SNK	raw	AllTags	not measured	68.26 [67.41, 69.12]	90.20 (Trankit large, UD 2.5; test changed) — MISS	87.35 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sk: UD_Slovak-SNK	raw	CLAS	not measured	87.18 [86.26, 88.16]	95.04 (Trankit large, UD 2.5; test changed) — MISS	84.43 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sk: UD_Slovak-SNK	raw	LAS	not measured	88.48 [87.67, 89.31]	95.60 (Trankit large, UD 2.5; test changed) — MISS	86.58 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sk: UD_Slovak-SNK	raw	Lemmas	not measured	91.29 [90.75, 91.76]	96.59 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.08 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sk: UD_Slovak-SNK	raw	MLAS	not measured	55.91 [54.76, 57.19]	87.64 (Trankit large, UD 2.5; test changed) — MISS	74.72 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sk: UD_Slovak-SNK	raw	Sentences	not measured	86.76 [84.86, 88.51]	98.49 (Trankit large, UD 2.5; test changed) — MISS	84.31 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sk: UD_Slovak-SNK	raw	Tokens	not measured	99.97 [99.93, 100.00]	99.96 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	99.96 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sk: UD_Slovak-SNK	raw	UAS	not measured	90.75 [90.04, 91.51]	96.97 (Trankit large, UD 2.5; test changed) — MISS	89.13 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sk: UD_Slovak-SNK	raw	UFeats	not measured	75.33 [74.50, 76.16]	95.22 (Trankit large, UD 2.5; test changed) — MISS	90.95 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sk: UD_Slovak-SNK	raw	UPOS	not measured	92.17 [91.70, 92.63]	97.90 (Trankit large, UD 2.5; test changed) — MISS	96.34 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sk: UD_Slovak-SNK	raw	Words	not measured	99.93 [99.88, 99.97]	100.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.96 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sk: UD_Slovak-SNK	raw	XPOS	not measured	71.71 [70.86, 72.58]	90.82 (Trankit large, UD 2.5; test changed) — MISS	88.19 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	gold	AllTags	not measured	74.45 [73.88, 75.05]	96.66 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sl: UD_Slovenian-SSJ	gold	CLAS	not measured	77.48 [76.61, 78.37]	not published	not published
sl: UD_Slovenian-SSJ	gold	LAS	not measured	81.88 [81.19, 82.57]	93.10 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sl: UD_Slovenian-SSJ	gold	Lemmas	not measured	92.93 [92.58, 93.27]	98.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sl: UD_Slovenian-SSJ	gold	MLAS	not measured	50.13 [49.19, 51.12]	87.50 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sl: UD_Slovenian-SSJ	gold	UAS	not measured	86.44 [85.81, 87.04]	94.65 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sl: UD_Slovenian-SSJ	gold	UFeats	not measured	78.15 [77.59, 78.70]	97.16 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sl: UD_Slovenian-SSJ	gold	UPOS	not measured	93.28 [92.91, 93.60]	98.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sl: UD_Slovenian-SSJ	gold	XPOS	not measured	78.26 [77.75, 78.80]	97.10 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sl: UD_Slovenian-SSJ	raw	AllTags	not measured	77.13 [76.59, 77.70]	97.60 (Trankit large, UD 2.5; test changed) — MISS	95.37 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	raw	CLAS	not measured	85.70 [84.98, 86.50]	94.88 (Trankit large, UD 2.5; test changed) — MISS	88.28 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	raw	LAS	not measured	88.30 [87.67, 89.00]	96.06 (Trankit large, UD 2.5; test changed) — MISS	90.80 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	raw	Lemmas	not measured	93.06 [92.68, 93.44]	98.69 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	97.69 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	raw	MLAS	not measured	58.69 [57.81, 59.66]	91.78 (Trankit large, UD 2.5; test changed) — MISS	83.80 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	raw	Sentences	not measured	96.78 [95.80, 97.68]	100.00 (Trankit large, UD 2.5; test changed) — MISS	99.26 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	raw	Tokens	not measured	99.20 [98.99, 99.41]	99.97 (Trankit large, UD 2.5; test changed) — MISS	99.93 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	raw	UAS	not measured	91.24 [90.64, 91.85]	96.91 (Trankit large, UD 2.5; test changed) — MISS	92.45 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	raw	UFeats	not measured	80.00 [79.46, 80.54]	97.99 (Trankit large, UD 2.5; test changed) — MISS	96.09 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	raw	UPOS	not measured	93.49 [93.10, 93.84]	99.24 (Trankit large, UD 2.5; test changed) — MISS	98.41 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	raw	Words	not measured	99.20 [98.99, 99.41]	99.97 (Trankit large, UD 2.5; test changed) — MISS	99.93 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sl: UD_Slovenian-SSJ	raw	XPOS	not measured	80.09 [79.60, 80.64]	97.83 (Trankit large, UD 2.5; test changed) — MISS	95.88 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sme: UD_North_Sami-Giella	gold	AllTags	not measured	62.16 [61.15, 63.19]	85.61 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sme: UD_North_Sami-Giella	gold	CLAS	not measured	52.19 [50.64, 53.68]	not published	not published
sme: UD_North_Sami-Giella	gold	LAS	not measured	55.43 [53.91, 56.87]	71.52 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sme: UD_North_Sami-Giella	gold	Lemmas	not measured	73.86 [72.93, 74.78]	87.05 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sme: UD_North_Sami-Giella	gold	MLAS	not measured	30.82 [29.58, 32.05]	60.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sme: UD_North_Sami-Giella	gold	UAS	not measured	64.22 [62.61, 65.69]	76.44 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sme: UD_North_Sami-Giella	gold	UFeats	not measured	69.28 [68.34, 70.28]	89.62 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sme: UD_North_Sami-Giella	gold	UPOS	not measured	81.63 [80.70, 82.42]	91.94 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sme: UD_North_Sami-Giella	gold	XPOS	not measured	84.71 [83.93, 85.40]	93.65 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sme: UD_North_Sami-Giella	raw	AllTags	not measured	65.57 [64.57, 66.61]	85.48 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	83.69 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sme: UD_North_Sami-Giella	raw	CLAS	not measured	60.76 [59.17, 62.39]	64.19 (Stanza 1.5.1, UD 2.12; test same size) — MISS	64.19 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sme: UD_North_Sami-Giella	raw	LAS	not measured	63.12 [61.54, 64.64]	71.26 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	66.63 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sme: UD_North_Sami-Giella	raw	Lemmas	not measured	74.79 [73.90, 75.67]	88.54 (Stanza 1.5.1, UD 2.12; test same size) — MISS	88.54 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sme: UD_North_Sami-Giella	raw	MLAS	not measured	38.33 [36.89, 39.78]	60.71 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	57.21 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sme: UD_North_Sami-Giella	raw	Sentences	not measured	96.12 [94.45, 97.45]	99.65 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.65 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sme: UD_North_Sami-Giella	raw	Tokens	not measured	98.83 [98.49, 99.14]	99.71 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.71 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sme: UD_North_Sami-Giella	raw	UAS	not measured	70.90 [69.24, 72.42]	76.20 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	72.26 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sme: UD_North_Sami-Giella	raw	UFeats	not measured	71.50 [70.52, 72.50]	89.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	88.08 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sme: UD_North_Sami-Giella	raw	UPOS	not measured	84.08 [83.28, 84.85]	91.83 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	90.73 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sme: UD_North_Sami-Giella	raw	Words	not measured	98.83 [98.49, 99.14]	99.87 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	99.71 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sme: UD_North_Sami-Giella	raw	XPOS	not measured	87.64 [86.90, 88.36]	93.50 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	92.77 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sms: UD_Skolt_Sami-Giellagas	gold	AllTags	not measured	13.36 [11.90, 14.74]	not published	not published
sms: UD_Skolt_Sami-Giellagas	gold	CLAS	not measured	17.59 [15.73, 19.70]	not published	not published
sms: UD_Skolt_Sami-Giellagas	gold	LAS	not measured	22.10 [20.21, 24.31]	not published	not published
sms: UD_Skolt_Sami-Giellagas	gold	Lemmas	not measured	60.88 [59.19, 62.36]	not published	not published
sms: UD_Skolt_Sami-Giellagas	gold	MLAS	not measured	1.20 [0.68, 1.78]	not published	not published
sms: UD_Skolt_Sami-Giellagas	gold	UAS	not measured	38.47 [35.74, 41.39]	not published	not published
sms: UD_Skolt_Sami-Giellagas	gold	UFeats	not measured	42.75 [41.38, 44.19]	not published	not published
sms: UD_Skolt_Sami-Giellagas	gold	UPOS	not measured	35.15 [33.65, 36.84]	not published	not published
sms: UD_Skolt_Sami-Giellagas	gold	XPOS	not measured	35.67 [33.71, 37.69]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	AllTags	not measured	16.68 [15.23, 18.12]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	CLAS	not measured	12.62 [10.80, 14.79]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	LAS	not measured	16.40 [14.47, 18.50]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	Lemmas	not measured	61.05 [59.43, 62.51]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	MLAS	not measured	0.97 [0.58, 1.41]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	Sentences	not measured	16.62 [11.32, 22.16]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	Tokens	not measured	100.00 [100.00, 100.00]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	UAS	not measured	28.87 [26.11, 31.77]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	UFeats	not measured	42.27 [40.76, 43.69]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	UPOS	not measured	39.33 [37.74, 41.08]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	Words	not measured	100.00 [100.00, 100.00]	not published	not published
sms: UD_Skolt_Sami-Giellagas	raw	XPOS	not measured	41.30 [39.05, 43.34]	not published	not published
sq: UD_Albanian-STAF	gold	CLAS	not measured	60.05 [52.05, 69.94]	not published	not published
sq: UD_Albanian-STAF	gold	LAS	not measured	67.74 [62.23, 74.29]	64.52 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sq: UD_Albanian-STAF	gold	Lemmas	not measured	80.65 [73.78, 86.16]	81.99 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sq: UD_Albanian-STAF	gold	MLAS	not measured	25.67 [19.54, 32.65]	33.09 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sq: UD_Albanian-STAF	gold	UAS	not measured	79.03 [73.76, 85.76]	77.15 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sq: UD_Albanian-STAF	gold	UFeats	not measured	61.02 [52.66, 68.93]	70.16 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sq: UD_Albanian-STAF	gold	UPOS	not measured	84.68 [80.45, 89.31]	88.71 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sq: UD_Albanian-STAF	raw	CLAS	not measured	60.78 [53.28, 70.55]	not published	not published
sq: UD_Albanian-STAF	raw	LAS	not measured	68.30 [61.94, 75.59]	65.86 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sq: UD_Albanian-STAF	raw	Lemmas	not measured	77.55 [70.55, 83.11]	80.65 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sq: UD_Albanian-STAF	raw	MLAS	not measured	27.45 [19.69, 36.47]	33.74 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sq: UD_Albanian-STAF	raw	Sentences	not measured	84.21 [66.67, 97.44]	92.68 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sq: UD_Albanian-STAF	raw	Tokens	not measured	99.59 [98.53, 100.00]	not published	not published
sq: UD_Albanian-STAF	raw	UAS	not measured	78.10 [73.22, 83.78]	77.96 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
sq: UD_Albanian-STAF	raw	UFeats	not measured	60.68 [51.60, 69.45]	70.16 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sq: UD_Albanian-STAF	raw	UPOS	not measured	82.18 [77.75, 86.79]	87.90 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sq: UD_Albanian-STAF	raw	Words	not measured	95.51 [92.25, 97.95]	98.39 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sr: UD_Serbian-SET	gold	AllTags	not measured	77.26 [76.37, 78.21]	95.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sr: UD_Serbian-SET	gold	CLAS	not measured	78.75 [77.56, 79.97]	not published	not published
sr: UD_Serbian-SET	gold	LAS	not measured	81.81 [80.86, 82.86]	91.77 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sr: UD_Serbian-SET	gold	Lemmas	not measured	91.91 [91.34, 92.48]	97.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sr: UD_Serbian-SET	gold	MLAS	not measured	56.11 [54.67, 57.59]	84.29 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sr: UD_Serbian-SET	gold	UAS	not measured	85.84 [84.96, 86.71]	94.12 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sr: UD_Serbian-SET	gold	UFeats	not measured	80.98 [80.12, 81.87]	96.19 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sr: UD_Serbian-SET	gold	UPOS	not measured	93.67 [93.13, 94.19]	99.06 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sr: UD_Serbian-SET	gold	XPOS	not measured	81.84 [81.03, 82.68]	96.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sr: UD_Serbian-SET	raw	AllTags	not measured	81.57 [80.81, 82.38]	95.84 (Trankit large, UD 2.5; test same size) — MISS	93.76 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sr: UD_Serbian-SET	raw	CLAS	not measured	86.02 [84.98, 87.10]	91.92 (Trankit large, UD 2.5; test same size) — MISS	85.92 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sr: UD_Serbian-SET	raw	LAS	not measured	88.01 [87.10, 88.97]	93.13 (Trankit large, UD 2.5; test same size) — MISS	88.36 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sr: UD_Serbian-SET	raw	Lemmas	not measured	92.61 [92.05, 93.13]	97.96 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	96.30 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sr: UD_Serbian-SET	raw	MLAS	not measured	66.16 [64.76, 67.54]	85.76 (Trankit large, UD 2.5; test same size) — MISS	78.82 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sr: UD_Serbian-SET	raw	Sentences	not measured	92.20 [90.01, 94.20]	100.00 (Trankit large, UD 2.5; test same size) — MISS	98.46 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sr: UD_Serbian-SET	raw	Tokens	not measured	98.80 [98.53, 99.06]	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sr: UD_Serbian-SET	raw	UAS	not measured	90.90 [90.04, 91.74]	95.57 (Trankit large, UD 2.5; test same size) — MISS	91.44 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sr: UD_Serbian-SET	raw	UFeats	not measured	84.64 [83.87, 85.41]	96.40 (Trankit large, UD 2.5; test same size) — MISS	94.31 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sr: UD_Serbian-SET	raw	UPOS	not measured	94.92 [94.49, 95.34]	99.06 (Trankit large, UD 2.5; test same size) — MISS	98.44 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sr: UD_Serbian-SET	raw	Words	not measured	98.80 [98.53, 99.06]	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.99 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sr: UD_Serbian-SET	raw	XPOS	not measured	84.12 [83.36, 84.87]	96.22 (Trankit large, UD 2.5; test same size) — MISS	94.16 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sv: UD_Swedish-Talbanken	gold	AllTags	not measured	86.03 [85.49, 86.53]	96.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sv: UD_Swedish-Talbanken	gold	CLAS	not measured	79.60 [78.66, 80.53]	not published	not published
sv: UD_Swedish-Talbanken	gold	LAS	not measured	82.89 [82.06, 83.67]	91.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sv: UD_Swedish-Talbanken	gold	Lemmas	not measured	96.25 [95.98, 96.50]	98.66 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sv: UD_Swedish-Talbanken	gold	MLAS	not measured	64.57 [63.52, 65.53]	85.23 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sv: UD_Swedish-Talbanken	gold	UAS	not measured	86.74 [85.99, 87.46]	93.39 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sv: UD_Swedish-Talbanken	gold	UFeats	not measured	90.07 [89.62, 90.48]	97.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sv: UD_Swedish-Talbanken	gold	UPOS	not measured	96.74 [96.45, 97.00]	98.79 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sv: UD_Swedish-Talbanken	gold	XPOS	not measured	90.35 [89.90, 90.79]	97.44 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
sv: UD_Swedish-Talbanken	raw	AllTags	not measured	87.64 [87.17, 88.10]	97.43 (Trankit large, UD 2.5; test same size) — MISS	96.24 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sv: UD_Swedish-Talbanken	raw	CLAS	not measured	85.59 [84.73, 86.44]	92.08 (Trankit large, UD 2.5; test same size) — MISS	85.91 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sv: UD_Swedish-Talbanken	raw	LAS	not measured	87.66 [86.83, 88.46]	92.97 (Trankit large, UD 2.5; test same size) — MISS	87.85 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sv: UD_Swedish-Talbanken	raw	Lemmas	not measured	96.46 [96.20, 96.73]	98.53 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	97.92 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sv: UD_Swedish-Talbanken	raw	MLAS	not measured	72.70 [71.71, 73.66]	88.67 (Trankit large, UD 2.5; test same size) — MISS	81.88 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sv: UD_Swedish-Talbanken	raw	Sentences	not measured	95.84 [94.86, 96.79]	99.38 (Trankit base, UD 2.5; test same size) — MISS	97.49 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sv: UD_Swedish-Talbanken	raw	Tokens	not measured	99.36 [99.22, 99.50]	99.97 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.97 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sv: UD_Swedish-Talbanken	raw	UAS	not measured	90.67 [89.94, 91.38]	94.41 (Trankit large, UD 2.5; test same size) — MISS	90.32 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
sv: UD_Swedish-Talbanken	raw	UFeats	not measured	91.02 [90.62, 91.42]	98.04 (Trankit large, UD 2.5; test same size) — MISS	97.29 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sv: UD_Swedish-Talbanken	raw	UPOS	not measured	96.83 [96.55, 97.10]	99.06 (Trankit large, UD 2.5; test same size) — MISS	98.28 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sv: UD_Swedish-Talbanken	raw	Words	not measured	99.36 [99.22, 99.50]	99.97 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.97 (Stanza 1.5.1, UD 2.12; test same size) — MISS
sv: UD_Swedish-Talbanken	raw	XPOS	not measured	90.73 [90.30, 91.15]	98.09 (Trankit large, UD 2.5; test same size) — MISS	97.13 (Stanza 1.5.1, UD 2.12; test same size) — MISS
te: UD_Telugu-MTG	gold	AllTags	not measured	94.45 [92.55, 96.23]	94.04 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
te: UD_Telugu-MTG	gold	CLAS	not measured	77.67 [73.36, 82.27]	not published	not published
te: UD_Telugu-MTG	gold	LAS	not measured	81.41 [77.48, 85.31]	85.16 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
te: UD_Telugu-MTG	gold	MLAS	not measured	73.09 [68.09, 78.28]	77.86 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
te: UD_Telugu-MTG	gold	UAS	not measured	90.71 [87.60, 93.74]	91.26 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
te: UD_Telugu-MTG	gold	UFeats	not measured	98.89 [97.83, 99.72]	98.89 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
te: UD_Telugu-MTG	gold	UPOS	not measured	94.45 [92.55, 96.23]	94.17 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
te: UD_Telugu-MTG	gold	XPOS	not measured	94.45 [92.55, 96.23]	94.17 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
te: UD_Telugu-MTG	raw	AllTags	not measured	93.42 [91.41, 95.40]	94.32 (Trankit base, UD 2.5; test same size) — within or ahead	93.97 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
te: UD_Telugu-MTG	raw	CLAS	not measured	81.14 [76.68, 85.38]	84.46 (Trankit large, UD 2.5; test same size) — within or ahead	78.13 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
te: UD_Telugu-MTG	raw	LAS	not measured	84.13 [80.47, 87.77]	87.08 (Trankit large, UD 2.5; test same size) — within or ahead	81.64 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
te: UD_Telugu-MTG	raw	MLAS	not measured	75.81 [71.10, 80.64]	80.65 (Trankit large, UD 2.5; test same size) — MISS	74.50 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
te: UD_Telugu-MTG	raw	Sentences	not measured	89.68 [85.09, 94.04]	98.62 (Stanza 1.5.1, UD 2.12; test same size) — MISS	98.62 (Stanza 1.5.1, UD 2.12; test same size) — MISS
te: UD_Telugu-MTG	raw	Tokens	not measured	99.79 [99.35, 100.00]	99.79 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	99.79 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
te: UD_Telugu-MTG	raw	UAS	not measured	91.20 [88.35, 94.05]	93.19 (Trankit large, UD 2.5; test same size) — within or ahead	90.09 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
te: UD_Telugu-MTG	raw	UFeats	not measured	98.54 [97.49, 99.57]	99.10 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	99.10 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
te: UD_Telugu-MTG	raw	UPOS	not measured	93.42 [91.41, 95.40]	94.32 (Trankit base, UD 2.5; test same size) — within or ahead	93.97 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
te: UD_Telugu-MTG	raw	Words	not measured	99.79 [99.35, 100.00]	99.79 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	99.79 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
te: UD_Telugu-MTG	raw	XPOS	not measured	93.42 [91.41, 95.40]	94.32 (Trankit base, UD 2.5; test same size) — within or ahead	93.97 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
th: UD_Thai-TUD	gold	CLAS	not measured	57.88 [56.17, 59.81]	not published	not published
th: UD_Thai-TUD	gold	LAS	not measured	61.77 [60.27, 63.62]	71.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
th: UD_Thai-TUD	gold	MLAS	not measured	48.08 [46.44, 49.91]	61.35 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
th: UD_Thai-TUD	gold	UAS	not measured	73.57 [72.28, 74.97]	81.27 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
th: UD_Thai-TUD	gold	UFeats	not measured	100.00 [100.00, 100.00]	100.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
th: UD_Thai-TUD	gold	UPOS	not measured	85.27 [84.38, 86.17]	89.39 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
th: UD_Thai-TUD	raw	CLAS	not measured	42.94 [40.91, 44.91]	not published	not published
th: UD_Thai-TUD	raw	LAS	not measured	47.69 [45.84, 49.59]	50.87 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
th: UD_Thai-TUD	raw	MLAS	not measured	34.82 [32.93, 36.61]	41.01 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
th: UD_Thai-TUD	raw	Sentences	not measured	26.10 [20.93, 31.02]	11.36 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
th: UD_Thai-TUD	raw	Tokens	not measured	88.26 [87.23, 89.24]	not published	not published
th: UD_Thai-TUD	raw	UAS	not measured	57.38 [55.53, 59.28]	58.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
th: UD_Thai-TUD	raw	UFeats	not measured	88.26 [87.23, 89.24]	87.14 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
th: UD_Thai-TUD	raw	UPOS	not measured	73.95 [72.71, 75.22]	77.29 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
th: UD_Thai-TUD	raw	Words	not measured	88.26 [87.23, 89.24]	87.14 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
tr: UD_Turkish-BOUN	gold	AllTags	not measured	37.77 [37.03, 38.61]	73.41 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
tr: UD_Turkish-BOUN	gold	CLAS	not measured	65.35 [63.77, 66.74]	not published	not published
tr: UD_Turkish-BOUN	gold	LAS	67.92 [66.56, 69.24]	67.13 [65.67, 68.45]	74.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
tr: UD_Turkish-BOUN	gold	Lemmas	86.40 [85.75, 87.00]	86.00 [85.31, 86.61]	93.62 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
tr: UD_Turkish-BOUN	gold	MLAS	not measured	45.80 [44.46, 47.03]	52.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
tr: UD_Turkish-BOUN	gold	UAS	75.25 [73.92, 76.56]	74.44 [73.05, 75.76]	80.54 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
tr: UD_Turkish-BOUN	gold	UFeats	80.57 [79.80, 81.33]	80.29 [79.54, 81.01]	83.03 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
tr: UD_Turkish-BOUN	gold	UPOS	91.50 [90.98, 92.05]	91.28 [90.72, 91.81]	93.14 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
tr: UD_Turkish-BOUN	gold	XPOS	not measured	44.67 [43.81, 45.55]	89.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
tr: UD_Turkish-BOUN	raw	AllTags	not measured	37.44 [36.68, 38.26]	73.03 (Stanza 1.5.1, UD 2.12; test same size) — MISS	73.03 (Stanza 1.5.1, UD 2.12; test same size) — MISS
tr: UD_Turkish-BOUN	raw	CLAS	not measured	63.21 [61.68, 64.58]	63.79 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	63.79 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
tr: UD_Turkish-BOUN	raw	LAS	63.03 [61.61, 64.41]	64.31 [62.89, 65.78]	67.27 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	65.17 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
tr: UD_Turkish-BOUN	raw	Lemmas	84.51 [83.78, 85.20]	84.42 [83.71, 85.09]	90.59 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	90.37 (Stanza 1.5.1, UD 2.12; test same size) — MISS
tr: UD_Turkish-BOUN	raw	MLAS	not measured	46.89 [45.51, 48.21]	49.26 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	48.49 (Stanza 1.5.1, UD 2.12; test same size) — MISS
tr: UD_Turkish-BOUN	raw	Sentences	81.28 [78.81, 83.58]	78.82 [76.14, 81.22]	90.08 (Stanza 1.5.1, UD 2.12; test same size) — MISS	90.08 (Stanza 1.5.1, UD 2.12; test same size) — MISS
tr: UD_Turkish-BOUN	raw	Tokens	99.56 [99.41, 99.71]	99.56 [99.41, 99.71]	99.58 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	99.58 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
tr: UD_Turkish-BOUN	raw	UAS	69.75 [68.39, 71.06]	71.15 [69.82, 72.44]	73.16 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	71.53 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
tr: UD_Turkish-BOUN	raw	UFeats	80.24 [79.44, 81.03]	80.23 [79.44, 81.03]	81.66 (Stanza 1.5.1, UD 2.12; test same size) — MISS	81.66 (Stanza 1.5.1, UD 2.12; test same size) — MISS
tr: UD_Turkish-BOUN	raw	UPOS	89.08 [88.46, 89.72]	88.62 [87.99, 89.32]	90.01 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	89.92 (Stanza 1.5.1, UD 2.12; test same size) — MISS
tr: UD_Turkish-BOUN	raw	Words	96.71 [96.34, 97.08]	96.71 [96.34, 97.08]	96.57 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	96.32 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
tr: UD_Turkish-BOUN	raw	XPOS	not measured	43.51 [42.62, 44.33]	86.01 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	85.74 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ug: UD_Uyghur-UDT	gold	AllTags	not measured	54.59 [53.68, 55.49]	81.17 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ug: UD_Uyghur-UDT	gold	CLAS	not measured	46.41 [45.08, 47.78]	not published	not published
ug: UD_Uyghur-UDT	gold	LAS	not measured	51.62 [50.37, 52.94]	66.62 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ug: UD_Uyghur-UDT	gold	Lemmas	not measured	91.36 [90.75, 91.99]	95.15 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ug: UD_Uyghur-UDT	gold	MLAS	not measured	23.01 [21.96, 24.06]	51.26 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ug: UD_Uyghur-UDT	gold	UAS	not measured	65.46 [64.08, 66.72]	77.54 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ug: UD_Uyghur-UDT	gold	UFeats	not measured	65.89 [65.03, 66.75]	88.51 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ug: UD_Uyghur-UDT	gold	UPOS	not measured	78.97 [78.20, 79.76]	90.26 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ug: UD_Uyghur-UDT	gold	XPOS	not measured	81.13 [80.38, 81.97]	92.33 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
ug: UD_Uyghur-UDT	raw	AllTags	not measured	56.36 [55.37, 57.27]	80.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	80.06 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ug: UD_Uyghur-UDT	raw	CLAS	not measured	53.55 [52.19, 55.00]	66.06 (Trankit large, UD 2.5; test same size) — MISS	58.96 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ug: UD_Uyghur-UDT	raw	LAS	not measured	58.25 [56.97, 59.60]	70.14 (Trankit large, UD 2.5; test same size) — MISS	63.42 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ug: UD_Uyghur-UDT	raw	Lemmas	not measured	91.17 [90.51, 91.81]	95.30 (Stanza 1.5.1, UD 2.12; test same size) — MISS	95.30 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ug: UD_Uyghur-UDT	raw	MLAS	not measured	27.61 [26.39, 28.77]	51.63 (Trankit large, UD 2.5; test same size) — MISS	48.01 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ug: UD_Uyghur-UDT	raw	Sentences	not measured	77.41 [74.83, 80.10]	88.95 (Trankit large, UD 2.5; test same size) — MISS	84.69 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ug: UD_Uyghur-UDT	raw	Tokens	not measured	99.57 [99.35, 99.75]	99.42 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	99.42 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
ug: UD_Uyghur-UDT	raw	UAS	not measured	72.12 [70.81, 73.47]	80.19 (Trankit large, UD 2.5; test same size) — MISS	74.80 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ug: UD_Uyghur-UDT	raw	UFeats	not measured	67.20 [66.28, 68.12]	88.03 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	87.58 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ug: UD_Uyghur-UDT	raw	UPOS	not measured	80.12 [79.30, 80.95]	89.87 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	89.26 (Stanza 1.5.1, UD 2.12; test same size) — MISS
ug: UD_Uyghur-UDT	raw	Words	not measured	99.57 [99.35, 99.75]	99.54 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	99.42 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
ug: UD_Uyghur-UDT	raw	XPOS	not measured	82.75 [82.01, 83.52]	91.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	91.19 (Stanza 1.5.1, UD 2.12; test same size) — MISS
uk: UD_Ukrainian-ParlaMint	gold	AllTags	not measured	74.30 [73.28, 75.29]	93.81 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	gold	CLAS	not measured	79.88 [78.76, 81.01]	not published	not published
uk: UD_Ukrainian-ParlaMint	gold	LAS	not measured	81.97 [80.94, 82.94]	91.92 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	gold	Lemmas	not measured	95.04 [94.60, 95.51]	99.12 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	gold	MLAS	not measured	52.19 [50.73, 53.66]	82.96 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	gold	UAS	not measured	86.02 [85.07, 86.91]	93.96 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	gold	UFeats	not measured	76.60 [75.66, 77.59]	95.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	gold	UPOS	not measured	94.32 [93.84, 94.79]	98.60 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	gold	XPOS	not measured	95.96 [95.55, 96.34]	98.49 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	raw	AllTags	not measured	76.62 [75.63, 77.58]	93.81 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	raw	CLAS	not measured	84.71 [83.72, 85.70]	not published	not published
uk: UD_Ukrainian-ParlaMint	raw	LAS	not measured	87.15 [86.25, 87.96]	91.91 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	raw	Lemmas	not measured	95.83 [95.46, 96.22]	99.07 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	raw	MLAS	not measured	57.47 [56.07, 58.80]	82.96 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	raw	Sentences	not measured	91.06 [89.16, 92.92]	99.81 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	raw	Tokens	not measured	99.96 [99.91, 100.00]	not published	not published
uk: UD_Ukrainian-ParlaMint	raw	UAS	not measured	90.59 [89.79, 91.34]	93.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	raw	UFeats	not measured	78.33 [77.39, 79.27]	95.01 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	raw	UPOS	not measured	94.91 [94.48, 95.32]	98.56 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uk: UD_Ukrainian-ParlaMint	raw	Words	not measured	99.96 [99.91, 100.00]	99.95 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
uk: UD_Ukrainian-ParlaMint	raw	XPOS	not measured	96.74 [96.40, 97.08]	98.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
uz: UD_Uzbek-UzUDT	gold	AllTags	not measured	52.94 [50.05, 55.77]	60.21 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
uz: UD_Uzbek-UzUDT	gold	CLAS	not measured	47.89 [44.82, 50.61]	not published	not published
uz: UD_Uzbek-UzUDT	gold	LAS	not measured	52.10 [49.27, 54.95]	57.97 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
uz: UD_Uzbek-UzUDT	gold	Lemmas	not measured	78.41 [76.68, 80.28]	29.22 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	not published
uz: UD_Uzbek-UzUDT	gold	MLAS	not measured	21.68 [19.53, 24.18]	30.19 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
uz: UD_Uzbek-UzUDT	gold	UAS	not measured	67.80 [65.04, 70.66]	73.63 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
uz: UD_Uzbek-UzUDT	gold	UFeats	not measured	61.87 [59.49, 64.40]	70.49 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
uz: UD_Uzbek-UzUDT	gold	UPOS	not measured	84.77 [83.18, 86.33]	86.24 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	not published
uz: UD_Uzbek-UzUDT	gold	XPOS	not measured	83.36 [80.32, 86.10]	85.58 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	not published
uz: UD_Uzbek-UzUDT	raw	AllTags	not measured	54.86 [52.05, 57.56]	60.26 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
uz: UD_Uzbek-UzUDT	raw	CLAS	not measured	52.43 [49.35, 55.39]	not published	not published
uz: UD_Uzbek-UzUDT	raw	LAS	not measured	56.59 [53.81, 59.44]	55.78 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	not published
uz: UD_Uzbek-UzUDT	raw	Lemmas	not measured	80.14 [78.47, 81.87]	29.27 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	not published
uz: UD_Uzbek-UzUDT	raw	MLAS	not measured	26.44 [23.96, 29.29]	28.87 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	not published
uz: UD_Uzbek-UzUDT	raw	Sentences	not measured	70.95 [64.41, 76.45]	72.26 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	not published
uz: UD_Uzbek-UzUDT	raw	Tokens	not measured	100.00 [100.00, 100.00]	not published	not published
uz: UD_Uzbek-UzUDT	raw	UAS	not measured	71.68 [68.90, 74.38]	71.16 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	not published
uz: UD_Uzbek-UzUDT	raw	UFeats	not measured	63.97 [61.65, 66.26]	70.68 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — MISS	not published
uz: UD_Uzbek-UzUDT	raw	UPOS	not measured	86.54 [85.03, 88.04]	86.15 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	not published
uz: UD_Uzbek-UzUDT	raw	Words	not measured	100.00 [100.00, 100.00]	100.00 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	not published
uz: UD_Uzbek-UzUDT	raw	XPOS	not measured	85.33 [82.30, 88.01]	85.25 (UDPipe 2 2.17 models 251125, UD 2.17; test changed) — within or ahead	not published
vi: UD_Vietnamese-VTB	gold	AllTags	not measured	86.23 [85.62, 86.85]	88.59 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
vi: UD_Vietnamese-VTB	gold	CLAS	not measured	57.91 [56.54, 59.19]	not published	not published
vi: UD_Vietnamese-VTB	gold	LAS	not measured	61.70 [60.51, 62.95]	65.51 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
vi: UD_Vietnamese-VTB	gold	Lemmas	not measured	99.30 [99.15, 99.44]	99.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
vi: UD_Vietnamese-VTB	gold	MLAS	not measured	48.86 [47.61, 50.15]	55.15 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
vi: UD_Vietnamese-VTB	gold	UAS	not measured	73.55 [72.37, 74.73]	75.84 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
vi: UD_Vietnamese-VTB	gold	UPOS	not measured	89.63 [89.04, 90.16]	89.92 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
vi: UD_Vietnamese-VTB	gold	XPOS	not measured	87.77 [87.21, 88.33]	88.74 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
vi: UD_Vietnamese-VTB	raw	AllTags	not measured	66.08 [65.06, 67.23]	88.07 (Trankit large, UD 2.5; test changed) — MISS	80.56 (Stanza 1.5.1, UD 2.12; test same size) — MISS
vi: UD_Vietnamese-VTB	raw	CLAS	not measured	34.08 [32.58, 35.61]	63.67 (Trankit large, UD 2.5; test changed) — MISS	46.60 (Stanza 1.5.1, UD 2.12; test same size) — MISS
vi: UD_Vietnamese-VTB	raw	LAS	not measured	38.80 [37.32, 40.34]	65.37 (Trankit large, UD 2.5; test changed) — MISS	51.49 (Stanza 1.5.1, UD 2.12; test same size) — MISS
vi: UD_Vietnamese-VTB	raw	Lemmas	not measured	74.75 [73.78, 75.75]	95.22 (Trankit base, UD 2.5; test changed) — MISS	81.66 (Stanza 1.5.1, UD 2.12; test same size) — MISS
vi: UD_Vietnamese-VTB	raw	MLAS	not measured	29.54 [28.16, 30.91]	60.22 (Trankit large, UD 2.5; test changed) — MISS	42.58 (Stanza 1.5.1, UD 2.12; test same size) — MISS
vi: UD_Vietnamese-VTB	raw	Sentences	not measured	90.38 [88.34, 92.39]	99.25 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.25 (Stanza 1.5.1, UD 2.12; test same size) — MISS
vi: UD_Vietnamese-VTB	raw	Tokens	not measured	75.25 [74.26, 76.27]	95.22 (Trankit base, UD 2.5; test changed) — MISS	88.02 (Stanza 1.5.1, UD 2.12; test same size) — MISS
vi: UD_Vietnamese-VTB	raw	UAS	not measured	44.71 [43.10, 46.33]	71.07 (Trankit large, UD 2.5; test changed) — MISS	58.82 (Stanza 1.5.1, UD 2.12; test same size) — MISS
vi: UD_Vietnamese-VTB	raw	UPOS	not measured	68.68 [67.63, 69.75]	89.70 (Trankit large, UD 2.5; test changed) — MISS	81.48 (Stanza 1.5.1, UD 2.12; test same size) — MISS
vi: UD_Vietnamese-VTB	raw	Words	not measured	75.25 [74.26, 76.27]	95.22 (Trankit base, UD 2.5; test changed) — MISS	88.02 (Stanza 1.5.1, UD 2.12; test same size) — MISS
vi: UD_Vietnamese-VTB	raw	XPOS	not measured	67.17 [66.14, 68.31]	88.14 (Trankit large, UD 2.5; test changed) — MISS	80.61 (Stanza 1.5.1, UD 2.12; test same size) — MISS
wo: UD_Wolof-WTB	gold	AllTags	not measured	65.36 [64.21, 66.41]	92.39 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
wo: UD_Wolof-WTB	gold	CLAS	not measured	44.54 [42.87, 46.19]	not published	not published
wo: UD_Wolof-WTB	gold	LAS	not measured	52.57 [51.05, 54.17]	80.16 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
wo: UD_Wolof-WTB	gold	Lemmas	not measured	87.49 [86.82, 88.16]	95.94 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
wo: UD_Wolof-WTB	gold	MLAS	not measured	27.49 [26.14, 28.82]	68.29 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
wo: UD_Wolof-WTB	gold	UAS	not measured	63.82 [62.37, 65.41]	85.75 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
wo: UD_Wolof-WTB	gold	UFeats	not measured	72.32 [71.33, 73.19]	94.33 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
wo: UD_Wolof-WTB	gold	UPOS	not measured	79.61 [78.71, 80.53]	95.29 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
wo: UD_Wolof-WTB	gold	XPOS	not measured	79.43 [78.38, 80.41]	95.14 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
wo: UD_Wolof-WTB	raw	AllTags	not measured	64.26 [63.16, 65.31]	91.44 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	91.38 (Stanza 1.5.1, UD 2.12; test same size) — MISS
wo: UD_Wolof-WTB	raw	CLAS	not measured	48.57 [46.94, 50.19]	71.22 (Stanza 1.5.1, UD 2.12; test same size) — MISS	71.22 (Stanza 1.5.1, UD 2.12; test same size) — MISS
wo: UD_Wolof-WTB	raw	LAS	not measured	56.10 [54.60, 57.59]	78.02 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	77.32 (Stanza 1.5.1, UD 2.12; test same size) — MISS
wo: UD_Wolof-WTB	raw	Lemmas	not measured	84.43 [83.62, 85.26]	95.18 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.63 (Stanza 1.5.1, UD 2.12; test same size) — MISS
wo: UD_Wolof-WTB	raw	MLAS	not measured	30.16 [28.77, 31.48]	66.05 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	64.89 (Stanza 1.5.1, UD 2.12; test same size) — MISS
wo: UD_Wolof-WTB	raw	Sentences	not measured	91.55 [88.99, 93.80]	94.33 (Stanza 1.5.1, UD 2.12; test same size) — MISS	94.33 (Stanza 1.5.1, UD 2.12; test same size) — MISS
wo: UD_Wolof-WTB	raw	Tokens	not measured	99.93 [99.84, 99.99]	99.95 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead	99.95 (Stanza 1.5.1, UD 2.12; test same size) — within or ahead
wo: UD_Wolof-WTB	raw	UAS	not measured	66.01 [64.54, 67.58]	83.49 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	83.28 (Stanza 1.5.1, UD 2.12; test same size) — MISS
wo: UD_Wolof-WTB	raw	UFeats	not measured	70.25 [69.32, 71.19]	93.47 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	93.19 (Stanza 1.5.1, UD 2.12; test same size) — MISS
wo: UD_Wolof-WTB	raw	UPOS	not measured	78.63 [77.67, 79.69]	94.36 (Stanza 1.5.1, UD 2.12; test same size) — MISS	94.36 (Stanza 1.5.1, UD 2.12; test same size) — MISS
wo: UD_Wolof-WTB	raw	Words	not measured	95.18 [94.64, 95.76]	99.35 (Stanza 1.5.1, UD 2.12; test same size) — MISS	99.35 (Stanza 1.5.1, UD 2.12; test same size) — MISS
wo: UD_Wolof-WTB	raw	XPOS	not measured	78.48 [77.53, 79.42]	94.24 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	94.16 (Stanza 1.5.1, UD 2.12; test same size) — MISS
yi: UD_Yiddish-YiTB	gold	CLAS	not measured	75.56 [73.82, 77.36]	not published	not published
yi: UD_Yiddish-YiTB	gold	LAS	not measured	81.00 [79.64, 82.38]	86.48 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	gold	Lemmas	not measured	91.14 [90.52, 91.75]	93.87 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	gold	MLAS	not measured	65.50 [63.65, 67.37]	76.74 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	gold	UAS	not measured	86.40 [85.18, 87.61]	90.34 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	gold	UFeats	not measured	100.00 [100.00, 100.00]	100.00 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — within or ahead	not published
yi: UD_Yiddish-YiTB	gold	UPOS	not measured	91.95 [91.35, 92.53]	94.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	raw	CLAS	not measured	76.89 [75.13, 78.55]	not published	not published
yi: UD_Yiddish-YiTB	raw	LAS	not measured	80.77 [79.38, 82.11]	85.56 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	raw	Lemmas	not measured	88.37 [87.63, 89.06]	93.53 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	raw	MLAS	not measured	68.47 [66.73, 70.19]	75.85 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	raw	Sentences	not measured	94.73 [93.41, 96.01]	97.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	raw	Tokens	not measured	98.32 [97.95, 98.70]	not published	not published
yi: UD_Yiddish-YiTB	raw	UAS	not measured	85.44 [84.17, 86.74]	89.38 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	raw	UFeats	not measured	96.17 [95.63, 96.70]	99.61 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	raw	UPOS	not measured	89.78 [89.11, 90.49]	94.50 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
yi: UD_Yiddish-YiTB	raw	Words	not measured	96.17 [95.63, 96.70]	99.61 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
zh: UD_Chinese-GSDSimp	gold	AllTags	85.15 [84.47, 85.82]	83.66 [82.95, 84.39]	95.20 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
zh: UD_Chinese-GSDSimp	gold	CLAS	not measured	59.72 [58.32, 61.19]	not published	not published
zh: UD_Chinese-GSDSimp	gold	LAS	63.29 [61.88, 64.70]	61.42 [60.21, 62.70]	83.60 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
zh: UD_Chinese-GSDSimp	gold	Lemmas	99.80 [99.71, 99.88]	99.78 [99.67, 99.86]	99.90 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
zh: UD_Chinese-GSDSimp	gold	MLAS	not measured	47.94 [46.40, 49.45]	77.62 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
zh: UD_Chinese-GSDSimp	gold	UAS	69.15 [67.81, 70.55]	67.22 [66.03, 68.48]	86.76 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
zh: UD_Chinese-GSDSimp	gold	UFeats	96.03 [95.69, 96.39]	95.86 [95.48, 96.23]	99.28 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
zh: UD_Chinese-GSDSimp	gold	UPOS	88.77 [88.18, 89.35]	87.55 [86.92, 88.22]	95.73 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
zh: UD_Chinese-GSDSimp	gold	XPOS	87.86 [87.24, 88.47]	87.14 [86.47, 87.79]	95.97 (UDPipe 2 2.17 models 251125, UD 2.17; test same size) — MISS	not published
zh: UD_Chinese-GSDSimp	raw	AllTags	77.97 [77.04, 78.87]	77.47 [76.54, 78.38]	94.32 (Trankit large, UD 2.5; test changed) — MISS	87.95 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zh: UD_Chinese-GSDSimp	raw	CLAS	not measured	58.05 [56.40, 59.67]	83.23 (Trankit large, UD 2.5; test changed) — MISS	67.39 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zh: UD_Chinese-GSDSimp	raw	LAS	58.84 [57.23, 60.35]	60.98 [59.49, 62.45]	84.63 (Trankit large, UD 2.5; test changed) — MISS	70.65 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zh: UD_Chinese-GSDSimp	raw	Lemmas	89.45 [88.61, 90.27]	89.41 [88.61, 90.21]	97.66 (Trankit large, UD 2.5; test changed) — MISS	92.07 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zh: UD_Chinese-GSDSimp	raw	MLAS	not measured	49.33 [47.69, 50.97]	79.84 (Trankit large, UD 2.5; test changed) — MISS	63.96 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zh: UD_Chinese-GSDSimp	raw	Sentences	85.31 [82.10, 88.41]	83.77 [80.32, 87.30]	99.70 (Trankit base, UD 2.5; test changed) — MISS	99.10 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zh: UD_Chinese-GSDSimp	raw	Tokens	89.62 [88.81, 90.43]	89.62 [88.81, 90.43]	97.66 (Trankit large, UD 2.5; test changed) — MISS	92.14 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zh: UD_Chinese-GSDSimp	raw	UAS	62.78 [61.24, 64.26]	64.42 [62.89, 65.87]	87.01 (Trankit large, UD 2.5; test changed) — MISS	73.41 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zh: UD_Chinese-GSDSimp	raw	UFeats	85.94 [85.11, 86.79]	85.98 [85.14, 86.82]	97.24 (Trankit large, UD 2.5; test changed) — MISS	91.47 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zh: UD_Chinese-GSDSimp	raw	UPOS	80.96 [80.07, 81.81]	80.66 [79.76, 81.48]	94.99 (Trankit large, UD 2.5; test changed) — MISS	88.82 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zh: UD_Chinese-GSDSimp	raw	Words	89.62 [88.81, 90.43]	89.62 [88.81, 90.43]	97.66 (Trankit large, UD 2.5; test changed) — MISS	92.14 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zh: UD_Chinese-GSDSimp	raw	XPOS	80.11 [79.28, 80.98]	79.75 [78.91, 80.63]	94.78 (Trankit large, UD 2.5; test changed) — MISS	88.61 (Stanza 1.5.1, UD 2.12; test changed) — MISS
zza: UD_Zazaki-ZSD	gold	CLAS	not measured	32.89 [25.34, 41.83]	not published	not published
zza: UD_Zazaki-ZSD	gold	LAS	not measured	39.60 [31.87, 48.95]	not published	not published
zza: UD_Zazaki-ZSD	gold	Lemmas	not measured	76.00 [69.52, 81.85]	not published	not published
zza: UD_Zazaki-ZSD	gold	MLAS	not measured	8.05 [3.88, 13.74]	not published	not published
zza: UD_Zazaki-ZSD	gold	UAS	not measured	56.00 [46.58, 66.49]	not published	not published
zza: UD_Zazaki-ZSD	gold	UFeats	not measured	51.20 [45.45, 57.41]	not published	not published
zza: UD_Zazaki-ZSD	gold	UPOS	not measured	63.20 [57.20, 69.49]	not published	not published
zza: UD_Zazaki-ZSD	raw	CLAS	not measured	33.00 [23.68, 41.45]	not published	not published
zza: UD_Zazaki-ZSD	raw	LAS	not measured	36.10 [26.64, 45.28]	not published	not published
zza: UD_Zazaki-ZSD	raw	Lemmas	not measured	67.63 [62.40, 72.44]	not published	not published
zza: UD_Zazaki-ZSD	raw	MLAS	not measured	8.08 [4.65, 11.95]	not published	not published
zza: UD_Zazaki-ZSD	raw	Sentences	not measured	83.33 [70.00, 93.55]	not published	not published
zza: UD_Zazaki-ZSD	raw	Tokens	not measured	100.00 [100.00, 100.00]	not published	not published
zza: UD_Zazaki-ZSD	raw	UAS	not measured	51.04 [39.65, 61.45]	not published	not published
zza: UD_Zazaki-ZSD	raw	UFeats	not measured	44.81 [40.29, 49.63]	not published	not published
zza: UD_Zazaki-ZSD	raw	UPOS	not measured	56.85 [52.63, 61.44]	not published	not published
zza: UD_Zazaki-ZSD	raw	Words	not measured	88.80 [83.68, 93.88]	not published	not published

Entity samples (gold tokens)

Deterministic evenly spaced samples, at most 3,001 sentences per corpus. The published UD references above do not supply comparable entity predictions; these rows are information. The paired spaCy view below uses identical sampled sentences.

Language	Metric	Before [95% CI]	Current [95% CI]
da	micro-F1	not measured	82.86 [78.88, 86.39]
da	micro-precision	not measured	83.91 [79.61, 88.03]
da	micro-recall	not measured	81.84 [77.26, 85.71]
de	micro-F1	82.68 [81.18, 84.04]	80.96 [79.47, 82.28]
de	micro-precision	85.82 [84.28, 87.23]	81.02 [79.37, 82.39]
de	micro-recall	79.77 [78.03, 81.32]	80.89 [79.30, 82.45]
en	micro-F1	79.07 [76.69, 81.48]	77.46 [74.74, 79.96]
en	micro-precision	86.13 [83.63, 88.42]	81.17 [77.98, 84.08]
en	micro-recall	73.07 [70.21, 76.07]	74.08 [71.08, 76.90]
es	micro-F1	85.58 [84.44, 86.59]	84.78 [83.64, 85.84]
es	micro-precision	85.97 [84.88, 87.00]	84.98 [83.82, 86.02]
es	micro-recall	85.19 [84.02, 86.29]	84.59 [83.41, 85.69]
fr	micro-F1	81.56 [80.48, 82.75]	80.96 [79.84, 82.17]
fr	micro-precision	82.11 [80.98, 83.29]	80.92 [79.71, 82.07]
fr	micro-recall	81.02 [79.97, 82.24]	81.01 [79.87, 82.22]
hr	micro-F1	not measured	81.87 [79.66, 84.04]
hr	micro-precision	not measured	82.03 [79.67, 84.46]
hr	micro-recall	not measured	81.71 [79.41, 83.67]
id	micro-F1	not measured	78.39 [74.93, 81.32]
id	micro-precision	not measured	82.68 [79.44, 85.53]
id	micro-recall	not measured	74.52 [70.15, 78.59]
it	micro-F1	86.30 [85.27, 87.25]	84.74 [83.65, 85.74]
it	micro-precision	86.57 [85.54, 87.48]	84.84 [83.74, 85.84]
it	micro-recall	86.03 [84.96, 87.02]	84.64 [83.48, 85.69]
nl	micro-F1	85.18 [84.06, 86.17]	83.70 [82.61, 84.70]
nl	micro-precision	84.85 [83.74, 85.88]	83.16 [82.06, 84.23]
nl	micro-recall	85.52 [84.42, 86.50]	84.24 [83.13, 85.25]
no	micro-F1	not measured	73.18 [70.65, 75.53]
no	micro-precision	not measured	69.24 [66.62, 71.93]
no	micro-recall	not measured	77.60 [75.15, 79.85]
pl	micro-F1	not measured	67.67 [65.13, 70.05]
pl	micro-precision	not measured	72.38 [69.44, 75.06]
pl	micro-recall	not measured	63.54 [60.98, 66.21]
pt	micro-F1	88.28 [86.43, 90.13]	88.30 [86.58, 90.01]
pt	micro-precision	90.14 [88.16, 92.00]	89.04 [87.14, 90.98]
pt	micro-recall	86.50 [84.43, 88.59]	87.57 [85.56, 89.54]
ro	micro-F1	not measured	67.70 [66.54, 68.89]
ro	micro-precision	not measured	70.80 [69.39, 72.13]
ro	micro-recall	not measured	64.87 [63.55, 66.15]
sk	micro-F1	not measured	65.10 [61.62, 68.69]
sk	micro-precision	not measured	63.51 [59.46, 67.53]
sk	micro-recall	not measured	66.78 [63.39, 70.22]
sl	micro-F1	not measured	68.03 [64.66, 71.79]
sl	micro-precision	not measured	70.97 [67.36, 74.92]
sl	micro-recall	not measured	65.32 [61.72, 69.26]
sr	micro-F1	not measured	89.92 [87.89, 91.79]
sr	micro-precision	not measured	91.79 [89.78, 93.63]
sr	micro-recall	not measured	88.12 [85.75, 90.43]
sv	micro-F1	not measured	69.35 [61.24, 76.73]
sv	micro-precision	not measured	88.19 [81.97, 93.48]
sv	micro-recall	not measured	57.14 [47.95, 65.96]
tr	micro-F1	83.55 [81.59, 85.40]	82.84 [80.81, 84.79]
tr	micro-precision	85.68 [83.58, 87.77]	82.65 [80.52, 84.71]
tr	micro-recall	81.51 [79.30, 83.56]	83.03 [80.86, 85.07]
zh	micro-F1	84.84 [81.89, 87.94]	84.04 [81.02, 86.97]
zh	micro-precision	86.51 [83.49, 89.63]	84.59 [81.42, 87.57]
zh	micro-recall	83.22 [79.76, 86.69]	83.49 [79.86, 86.79]

Paired spaCy 3.8.18 comparison (gate)

144 rows: 117 ahead, 14 within the paired interval, 13 behind. Same gold, mode and sampled entity sentences; 1,000 paired resamples, seed 20261106. spaCy runs its documented default configuration on the same training data. A row passes when it is ahead or within the paired interval; the 13 rows behind are gaps. Positive differences favor this model.

Language / dataset	Input	Metric	Current [95% CI]	spaCy [95% CI]	Difference [95% CI]	Verdict
de: de_gsd-ud-test	gold	UPOS	95.78 [95.43, 96.12]	94.59 [94.22, 94.97]	1.19 [0.80, 1.55]	ahead
de: de_gsd-ud-test	gold	UFeats	86.58 [85.91, 87.19]	84.71 [84.07, 85.40]	1.87 [1.16, 2.60]	ahead
de: de_gsd-ud-test	gold	Lemmas	96.64 [96.37, 96.92]	95.65 [95.32, 95.97]	0.99 [0.71, 1.27]	ahead
de: de_gsd-ud-test	gold	UAS	87.09 [86.26, 87.84]	81.88 [80.78, 82.88]	5.21 [4.40, 6.16]	ahead
de: de_gsd-ud-test	gold	LAS	83.49 [82.59, 84.31]	77.31 [76.19, 78.32]	6.18 [5.35, 7.14]	ahead
de: de_gsd-ud-test	raw	Tokens	97.40 [97.09, 97.69]	98.03 [97.67, 98.36]	-0.63 [-1.04, -0.21]	behind
de: de_gsd-ud-test	raw	Sentences	88.65 [86.73, 90.58]	78.73 [76.35, 81.37]	9.91 [7.13, 12.72]	ahead
de: de_gsd-ud-test	raw	Words	97.06 [96.70, 97.39]	95.51 [95.03, 95.96]	1.55 [1.22, 1.89]	ahead
de: de_gsd-ud-test	raw	UPOS	93.33 [92.87, 93.75]	90.13 [89.52, 90.69]	3.20 [2.76, 3.67]	ahead
de: de_gsd-ud-test	raw	UFeats	85.16 [84.51, 85.74]	80.11 [79.31, 80.89]	5.05 [4.33, 5.79]	ahead
de: de_gsd-ud-test	raw	Lemmas	94.07 [93.64, 94.48]	91.28 [90.71, 91.79]	2.80 [2.36, 3.25]	ahead
de: de_gsd-ud-test	raw	UAS	85.50 [84.64, 86.25]	75.30 [74.13, 76.35]	10.19 [9.36, 11.13]	ahead
de: de_gsd-ud-test	raw	LAS	82.38 [81.55, 83.18]	70.77 [69.60, 71.89]	11.61 [10.73, 12.52]	ahead
en: en_ewt-ud-test	gold	UPOS	96.49 [96.19, 96.76]	94.29 [93.88, 94.65]	2.20 [1.86, 2.57]	ahead
en: en_ewt-ud-test	gold	UFeats	96.37 [96.09, 96.62]	95.18 [94.87, 95.49]	1.19 [0.89, 1.50]	ahead
en: en_ewt-ud-test	gold	Lemmas	97.26 [97.01, 97.52]	95.80 [95.45, 96.12]	1.47 [1.21, 1.76]	ahead
en: en_ewt-ud-test	gold	UAS	88.34 [87.65, 89.01]	85.40 [84.51, 86.30]	2.93 [2.07, 3.81]	ahead
en: en_ewt-ud-test	gold	LAS	85.12 [84.40, 85.87]	81.96 [81.00, 82.88]	3.16 [2.30, 4.00]	ahead
en: en_ewt-ud-test	raw	Tokens	97.13 [96.83, 97.43]	95.70 [95.17, 96.16]	1.43 [1.00, 1.93]	ahead
en: en_ewt-ud-test	raw	Sentences	75.85 [74.20, 77.60]	72.66 [70.73, 74.67]	3.19 [1.22, 5.36]	ahead
en: en_ewt-ud-test	raw	Words	98.68 [98.45, 98.90]	97.48 [96.99, 97.96]	1.21 [0.78, 1.69]	ahead
en: en_ewt-ud-test	raw	UPOS	95.95 [95.59, 96.27]	92.45 [91.86, 93.05]	3.49 [2.96, 4.08]	ahead
en: en_ewt-ud-test	raw	UFeats	95.94 [95.61, 96.27]	93.37 [92.80, 93.92]	2.57 [2.07, 3.12]	ahead
en: en_ewt-ud-test	raw	Lemmas	96.39 [96.04, 96.74]	93.69 [93.08, 94.28]	2.70 [2.18, 3.28]	ahead
en: en_ewt-ud-test	raw	UAS	88.78 [88.07, 89.47]	81.34 [80.35, 82.35]	7.44 [6.58, 8.27]	ahead
en: en_ewt-ud-test	raw	LAS	86.55 [85.82, 87.26]	78.53 [77.47, 79.56]	8.01 [7.20, 8.84]	ahead
es: es_ancora-ud-test	gold	UPOS	98.00 [97.87, 98.14]	98.18 [98.03, 98.32]	-0.18 [-0.33, -0.03]	behind
es: es_ancora-ud-test	gold	UFeats	96.74 [96.58, 96.91]	97.74 [97.58, 97.89]	-1.00 [-1.17, -0.83]	behind
es: es_ancora-ud-test	gold	Lemmas	98.53 [98.42, 98.64]	98.72 [98.60, 98.83]	-0.19 [-0.30, -0.07]	behind
es: es_ancora-ud-test	gold	UAS	89.50 [89.08, 89.94]	89.04 [88.53, 89.51]	0.46 [0.02, 0.91]	ahead
es: es_ancora-ud-test	gold	LAS	86.97 [86.51, 87.42]	85.95 [85.40, 86.43]	1.03 [0.56, 1.50]	ahead
es: es_ancora-ud-test	raw	Tokens	99.84 [99.76, 99.90]	99.90 [99.85, 99.94]	-0.06 [-0.13, 0.01]	within
es: es_ancora-ud-test	raw	Sentences	97.05 [96.24, 97.78]	97.70 [96.94, 98.43]	-0.66 [-1.59, 0.28]	within
es: es_ancora-ud-test	raw	Words	99.83 [99.75, 99.89]	96.60 [96.38, 96.80]	3.23 [3.02, 3.45]	ahead
es: es_ancora-ud-test	raw	UPOS	98.20 [98.07, 98.34]	94.81 [94.55, 95.05]	3.40 [3.15, 3.64]	ahead
es: es_ancora-ud-test	raw	UFeats	96.83 [96.66, 96.99]	94.57 [94.32, 94.81]	2.25 [2.01, 2.50]	ahead
es: es_ancora-ud-test	raw	Lemmas	98.58 [98.46, 98.70]	95.37 [95.13, 95.59]	3.21 [2.98, 3.45]	ahead
es: es_ancora-ud-test	raw	UAS	91.93 [91.49, 92.31]	84.87 [84.27, 85.43]	7.06 [6.56, 7.55]	ahead
es: es_ancora-ud-test	raw	LAS	89.70 [89.24, 90.11]	81.82 [81.22, 82.40]	7.89 [7.37, 8.38]	ahead
fr: fr_gsd-ud-test	gold	UPOS	96.99 [96.60, 97.39]	97.07 [96.68, 97.47]	-0.09 [-0.49, 0.34]	within
fr: fr_gsd-ud-test	gold	UFeats	96.06 [95.58, 96.49]	96.41 [95.93, 96.85]	-0.35 [-0.90, 0.19]	within
fr: fr_gsd-ud-test	gold	Lemmas	98.03 [97.72, 98.31]	97.49 [97.13, 97.81]	0.54 [0.22, 0.88]	ahead
fr: fr_gsd-ud-test	gold	UAS	89.52 [88.61, 90.43]	89.10 [88.14, 90.12]	0.42 [-0.58, 1.43]	within
fr: fr_gsd-ud-test	gold	LAS	86.89 [85.93, 87.88]	85.98 [84.84, 87.07]	0.91 [-0.11, 1.95]	within
fr: fr_gsd-ud-test	raw	Tokens	99.88 [99.79, 99.96]	98.85 [98.49, 99.16]	1.02 [0.74, 1.37]	ahead
fr: fr_gsd-ud-test	raw	Sentences	92.65 [90.07, 94.98]	91.82 [89.08, 94.23]	0.83 [-1.20, 3.09]	within
fr: fr_gsd-ud-test	raw	Words	99.48 [99.29, 99.65]	94.64 [94.01, 95.17]	4.83 [4.31, 5.44]	ahead
fr: fr_gsd-ud-test	raw	UPOS	97.10 [96.71, 97.46]	91.80 [91.06, 92.46]	5.30 [4.66, 6.01]	ahead
fr: fr_gsd-ud-test	raw	UFeats	96.26 [95.82, 96.68]	91.16 [90.40, 91.86]	5.11 [4.40, 5.91]	ahead
fr: fr_gsd-ud-test	raw	Lemmas	97.96 [97.64, 98.25]	92.20 [91.44, 92.88]	5.76 [5.13, 6.48]	ahead
fr: fr_gsd-ud-test	raw	UAS	91.97 [91.12, 92.76]	81.64 [80.34, 82.90]	10.33 [9.24, 11.53]	ahead
fr: fr_gsd-ud-test	raw	LAS	89.78 [88.84, 90.63]	78.10 [76.76, 79.31]	11.68 [10.48, 12.84]	ahead
it: it_markit-ud-test	gold	UPOS	95.81 [95.39, 96.26]	92.20 [91.61, 92.77]	3.61 [3.05, 4.19]	ahead
it: it_markit-ud-test	gold	UFeats	92.12 [91.51, 92.73]	90.11 [89.46, 90.77]	2.01 [1.47, 2.63]	ahead
it: it_markit-ud-test	gold	Lemmas	86.38 [85.63, 87.08]	83.80 [82.97, 84.52]	2.58 [2.15, 3.03]	ahead
it: it_markit-ud-test	gold	UAS	82.05 [81.01, 83.15]	75.39 [74.12, 76.63]	6.66 [5.42, 7.96]	ahead
it: it_markit-ud-test	gold	LAS	77.63 [76.52, 78.78]	69.27 [67.94, 70.57]	8.36 [7.06, 9.75]	ahead
it: it_markit-ud-test	raw	Tokens	99.93 [99.86, 99.98]	95.76 [95.28, 96.24]	4.17 [3.69, 4.66]	ahead
it: it_markit-ud-test	raw	Sentences	90.11 [87.27, 92.93]	91.62 [88.51, 94.91]	-1.51 [-5.49, 1.94]	within
it: it_markit-ud-test	raw	Words	99.73 [99.58, 99.86]	88.66 [87.84, 89.43]	11.07 [10.30, 11.88]	ahead
it: it_markit-ud-test	raw	UPOS	96.12 [95.75, 96.52]	81.37 [80.37, 82.39]	14.75 [13.79, 15.79]	ahead
it: it_markit-ud-test	raw	UFeats	92.84 [92.29, 93.42]	81.05 [80.07, 82.01]	11.79 [10.85, 12.68]	ahead
it: it_markit-ud-test	raw	Lemmas	86.65 [85.93, 87.35]	73.64 [72.57, 74.71]	13.01 [12.18, 13.89]	ahead
it: it_markit-ud-test	raw	UAS	86.39 [85.36, 87.29]	62.66 [61.07, 64.19]	23.73 [22.07, 25.38]	ahead
it: it_markit-ud-test	raw	LAS	82.22 [81.04, 83.28]	56.71 [55.14, 58.22]	25.51 [23.86, 27.23]	ahead
de: germeval-2014	entities (gold)	micro-F1	80.96 [79.47, 82.28]	65.30 [63.38, 67.02]	15.66 [13.73, 17.43]	ahead
de: germeval-2014	entities (gold)	micro-precision	81.02 [79.37, 82.39]	70.48 [68.42, 72.31]	10.54 [8.39, 12.66]	ahead
de: germeval-2014	entities (gold)	micro-recall	80.89 [79.30, 82.45]	60.82 [58.79, 62.78]	20.07 [18.06, 21.89]	ahead
en: en_ewt-ud	entities (gold)	micro-F1	77.46 [74.74, 79.96]	62.32 [59.32, 65.10]	15.14 [12.00, 18.48]	ahead
en: en_ewt-ud	entities (gold)	micro-precision	81.17 [77.98, 84.08]	67.97 [64.61, 70.86]	13.20 [9.69, 17.10]	ahead
en: en_ewt-ud	entities (gold)	micro-recall	74.08 [71.08, 76.90]	57.54 [54.28, 60.60]	16.54 [12.93, 20.15]	ahead
es: wikiner-es-wp3	entities (gold)	micro-F1	84.78 [83.64, 85.84]	83.21 [82.13, 84.22]	1.57 [0.47, 2.70]	ahead
es: wikiner-es-wp3	entities (gold)	micro-precision	84.98 [83.82, 86.02]	83.79 [82.71, 84.80]	1.19 [0.01, 2.35]	ahead
es: wikiner-es-wp3	entities (gold)	micro-recall	84.59 [83.41, 85.69]	82.64 [81.49, 83.69]	1.95 [0.84, 3.08]	ahead
fr: wikiner-fr-wp3	entities (gold)	micro-F1	80.96 [79.84, 82.17]	75.52 [74.20, 76.84]	5.44 [4.14, 6.87]	ahead
fr: wikiner-fr-wp3	entities (gold)	micro-precision	80.92 [79.71, 82.07]	76.75 [75.45, 78.02]	4.17 [2.76, 5.63]	ahead
fr: wikiner-fr-wp3	entities (gold)	micro-recall	81.01 [79.87, 82.22]	74.33 [72.91, 75.76]	6.67 [5.35, 8.12]	ahead
it: wikiner-it-wp3	entities (gold)	micro-F1	84.74 [83.65, 85.74]	83.58 [82.47, 84.52]	1.16 [0.02, 2.24]	ahead
it: wikiner-it-wp3	entities (gold)	micro-precision	84.84 [83.74, 85.84]	84.08 [83.00, 85.06]	0.76 [-0.43, 1.90]	within
it: wikiner-it-wp3	entities (gold)	micro-recall	84.64 [83.48, 85.69]	83.09 [81.90, 84.07]	1.55 [0.41, 2.64]	ahead
nl: wikiner-nl-wp3	entities (gold)	micro-F1	83.70 [82.61, 84.70]	86.64 [85.63, 87.59]	-2.94 [-4.05, -1.85]	behind
nl: wikiner-nl-wp3	entities (gold)	micro-precision	83.16 [82.06, 84.23]	86.28 [85.24, 87.33]	-3.12 [-4.21, -2.02]	behind
nl: wikiner-nl-wp3	entities (gold)	micro-recall	84.24 [83.13, 85.25]	87.00 [85.96, 87.99]	-2.76 [-3.93, -1.65]	behind
pt: pt_bosque-ud	entities (gold)	micro-F1	88.30 [86.58, 90.01]	75.27 [72.77, 77.68]	13.03 [10.84, 15.42]	ahead
pt: pt_bosque-ud	entities (gold)	micro-precision	89.04 [87.14, 90.98]	76.96 [74.27, 79.75]	12.08 [9.54, 14.63]	ahead
pt: pt_bosque-ud	entities (gold)	micro-recall	87.57 [85.56, 89.54]	73.66 [70.89, 76.30]	13.91 [11.49, 16.67]	ahead
tr: turkish-wikiner	entities (gold)	micro-F1	82.84 [80.81, 84.79]	65.82 [63.46, 68.33]	17.01 [14.38, 19.32]	ahead
tr: turkish-wikiner	entities (gold)	micro-precision	82.65 [80.52, 84.71]	68.49 [65.67, 71.28]	14.15 [11.16, 16.97]	ahead
tr: turkish-wikiner	entities (gold)	micro-recall	83.03 [80.86, 85.07]	63.36 [60.70, 65.94]	19.67 [16.92, 22.08]	ahead
zh: zh_gsdsimp-ud	entities (gold)	micro-F1	84.04 [81.02, 86.97]	61.86 [57.51, 66.06]	22.17 [18.04, 26.66]	ahead
zh: zh_gsdsimp-ud	entities (gold)	micro-precision	84.59 [81.42, 87.57]	67.08 [62.38, 71.86]	17.52 [13.00, 22.28]	ahead
zh: zh_gsdsimp-ud	entities (gold)	micro-recall	83.49 [79.86, 86.79]	57.40 [52.59, 62.05]	26.08 [21.24, 31.29]	ahead
nl: nl_alpino-ud-test	gold	UPOS	96.91 [96.21, 97.44]	94.42 [93.78, 95.02]	2.49 [2.00, 3.00]	ahead
nl: nl_alpino-ud-test	gold	UFeats	96.62 [96.06, 97.12]	93.13 [92.47, 93.70]	3.49 [3.04, 3.95]	ahead
nl: nl_alpino-ud-test	gold	Lemmas	92.34 [91.80, 92.92]	91.83 [91.24, 92.37]	0.52 [0.15, 0.91]	ahead
nl: nl_alpino-ud-test	gold	UAS	90.23 [89.24, 91.11]	84.09 [82.87, 85.31]	6.14 [5.08, 7.25]	ahead
nl: nl_alpino-ud-test	gold	LAS	87.24 [86.15, 88.24]	79.85 [78.57, 81.13]	7.40 [6.20, 8.55]	ahead
nl: nl_alpino-ud-test	raw	Tokens	99.66 [99.46, 99.82]	99.82 [99.70, 99.93]	-0.16 [-0.34, 0.01]	within
nl: nl_alpino-ud-test	raw	Sentences	95.90 [94.35, 97.34]	89.60 [86.73, 92.03]	6.30 [3.78, 9.05]	ahead
nl: nl_alpino-ud-test	raw	Words	99.66 [99.46, 99.82]	99.82 [99.70, 99.93]	-0.16 [-0.34, 0.01]	within
nl: nl_alpino-ud-test	raw	UPOS	96.74 [96.11, 97.27]	94.36 [93.70, 94.95]	2.38 [1.88, 2.89]	ahead
nl: nl_alpino-ud-test	raw	UFeats	96.80 [96.29, 97.28]	92.97 [92.32, 93.58]	3.83 [3.33, 4.36]	ahead
nl: nl_alpino-ud-test	raw	Lemmas	92.05 [91.49, 92.67]	91.65 [91.06, 92.23]	0.40 [0.01, 0.86]	ahead
nl: nl_alpino-ud-test	raw	UAS	93.37 [92.55, 94.08]	83.70 [82.50, 84.92]	9.67 [8.60, 10.84]	ahead
nl: nl_alpino-ud-test	raw	LAS	91.11 [90.20, 91.92]	79.57 [78.38, 80.82]	11.54 [10.38, 12.58]	ahead
pt: pt_bosque-ud-test	gold	UPOS	96.10 [95.82, 96.36]	95.92 [95.66, 96.19]	0.18 [-0.12, 0.45]	within
pt: pt_bosque-ud-test	gold	UFeats	94.48 [94.16, 94.80]	94.11 [93.79, 94.41]	0.37 [0.04, 0.68]	ahead
pt: pt_bosque-ud-test	gold	Lemmas	97.59 [97.39, 97.79]	96.90 [96.69, 97.10]	0.69 [0.50, 0.90]	ahead
pt: pt_bosque-ud-test	gold	UAS	88.22 [87.63, 88.77]	86.05 [85.48, 86.64]	2.17 [1.54, 2.81]	ahead
pt: pt_bosque-ud-test	gold	LAS	84.54 [83.90, 85.14]	81.96 [81.32, 82.63]	2.58 [1.95, 3.26]	ahead
pt: pt_bosque-ud-test	raw	Tokens	99.86 [99.79, 99.92]	99.87 [99.80, 99.93]	-0.01 [-0.06, 0.05]	within
pt: pt_bosque-ud-test	raw	Sentences	93.50 [92.14, 94.81]	84.48 [82.18, 86.78]	9.02 [6.41, 11.50]	ahead
pt: pt_bosque-ud-test	raw	Words	99.26 [99.14, 99.38]	88.51 [88.07, 88.99]	10.76 [10.24, 11.20]	ahead
pt: pt_bosque-ud-test	raw	UPOS	96.75 [96.50, 96.98]	84.15 [83.63, 84.67]	12.60 [12.06, 13.09]	ahead
pt: pt_bosque-ud-test	raw	UFeats	95.19 [94.90, 95.48]	82.16 [81.65, 82.69]	13.03 [12.45, 13.58]	ahead
pt: pt_bosque-ud-test	raw	Lemmas	97.29 [97.09, 97.50]	85.35 [84.89, 85.85]	11.94 [11.47, 12.38]	ahead
pt: pt_bosque-ud-test	raw	UAS	90.68 [90.16, 91.19]	70.23 [69.40, 71.06]	20.45 [19.54, 21.32]	ahead
pt: pt_bosque-ud-test	raw	LAS	87.98 [87.39, 88.55]	65.85 [65.01, 66.74]	22.12 [21.20, 23.03]	ahead
tr: tr_boun-ud-test	gold	UPOS	91.28 [90.72, 91.81]	88.04 [87.40, 88.67]	3.24 [2.56, 3.86]	ahead
tr: tr_boun-ud-test	gold	UFeats	80.29 [79.54, 81.01]	78.30 [77.53, 79.14]	2.00 [1.32, 2.67]	ahead
tr: tr_boun-ud-test	gold	Lemmas	86.00 [85.31, 86.61]	80.24 [79.46, 80.94]	5.76 [5.11, 6.36]	ahead
tr: tr_boun-ud-test	gold	UAS	74.44 [73.05, 75.76]	67.44 [66.03, 68.71]	7.00 [5.68, 8.35]	ahead
tr: tr_boun-ud-test	gold	LAS	67.13 [65.67, 68.45]	57.87 [56.54, 59.16]	9.25 [7.98, 10.53]	ahead
tr: tr_boun-ud-test	raw	Tokens	99.56 [99.41, 99.71]	99.42 [99.26, 99.60]	0.14 [0.00, 0.27]	ahead
tr: tr_boun-ud-test	raw	Sentences	78.82 [76.14, 81.22]	82.09 [79.45, 84.67]	-3.28 [-6.27, -0.42]	behind
tr: tr_boun-ud-test	raw	Words	96.71 [96.34, 97.08]	97.06 [96.71, 97.41]	-0.35 [-0.70, 0.02]	within
tr: tr_boun-ud-test	raw	UPOS	88.62 [87.99, 89.32]	86.82 [86.12, 87.52]	1.80 [1.14, 2.48]	ahead
tr: tr_boun-ud-test	raw	UFeats	80.23 [79.44, 81.03]	77.20 [76.40, 78.07]	3.02 [2.35, 3.70]	ahead
tr: tr_boun-ud-test	raw	Lemmas	84.42 [83.71, 85.09]	78.83 [78.04, 79.58]	5.59 [4.98, 6.21]	ahead
tr: tr_boun-ud-test	raw	UAS	71.15 [69.82, 72.44]	63.96 [62.51, 65.35]	7.19 [5.92, 8.56]	ahead
tr: tr_boun-ud-test	raw	LAS	64.31 [62.89, 65.78]	55.86 [54.49, 57.22]	8.45 [7.26, 9.75]	ahead
zh: zh_gsdsimp-ud-test	gold	UPOS	87.55 [86.92, 88.22]	90.35 [89.68, 91.02]	-2.80 [-3.57, -1.97]	behind
zh: zh_gsdsimp-ud-test	gold	UFeats	95.86 [95.48, 96.23]	98.43 [98.21, 98.64]	-2.57 [-2.98, -2.17]	behind
zh: zh_gsdsimp-ud-test	gold	Lemmas	99.78 [99.67, 99.86]	99.91 [99.84, 99.96]	-0.13 [-0.22, -0.05]	behind
zh: zh_gsdsimp-ud-test	gold	UAS	67.22 [66.03, 68.48]	73.11 [71.58, 74.68]	-5.89 [-7.60, -4.07]	behind
zh: zh_gsdsimp-ud-test	gold	LAS	61.42 [60.21, 62.70]	68.24 [66.60, 69.90]	-6.83 [-8.61, -4.99]	behind
zh: zh_gsdsimp-ud-test	raw	Tokens	89.62 [88.81, 90.43]	39.43 [38.65, 40.19]	50.19 [48.99, 51.37]	ahead
zh: zh_gsdsimp-ud-test	raw	Sentences	83.77 [80.32, 87.30]	46.93 [42.54, 51.47]	36.84 [31.24, 42.38]	ahead
zh: zh_gsdsimp-ud-test	raw	Words	89.62 [88.81, 90.43]	39.43 [38.65, 40.19]	50.19 [48.99, 51.37]	ahead
zh: zh_gsdsimp-ud-test	raw	UPOS	80.66 [79.76, 81.48]	34.92 [34.21, 35.61]	45.73 [44.63, 46.91]	ahead
zh: zh_gsdsimp-ud-test	raw	UFeats	85.98 [85.14, 86.82]	38.38 [37.61, 39.14]	47.60 [46.37, 48.85]	ahead
zh: zh_gsdsimp-ud-test	raw	Lemmas	89.41 [88.61, 90.21]	39.43 [38.65, 40.19]	49.97 [48.77, 51.15]	ahead
zh: zh_gsdsimp-ud-test	raw	UAS	64.42 [62.89, 65.87]	9.12 [8.48, 9.79]	55.29 [53.62, 57.00]	ahead
zh: zh_gsdsimp-ud-test	raw	LAS	60.98 [59.49, 62.45]	8.59 [7.96, 9.24]	52.38 [50.74, 54.05]	ahead

Frozen-encoder parser recovery: original nine languages

English and Italian retain their exact previous files and reuse the corresponding previous test results. The other seven final heads were read once in each input mode after development selection; no test-driven continuation. Other heads, the encoder and all other languages are unchanged. Intervals use 1,000 resamples, seed 20261106.

Dataset	Input	Metric	Earlier nine-language model [95% CI]	Joint 84-language model [95% CI]	After parser recovery [95% CI]
de_gsd-ud-test	gold	UPOS	96.16 [95.83, 96.49]	95.78 [95.43, 96.12]	95.78 [95.43, 96.12]
de_gsd-ud-test	gold	XPOS	96.07 [95.71, 96.43]	95.84 [95.48, 96.19]	95.84 [95.48, 96.19]
de_gsd-ud-test	gold	AllTags	83.34 [82.57, 84.04]	83.09 [82.34, 83.75]	83.09 [82.34, 83.75]
de_gsd-ud-test	gold	UFeats	86.81 [86.11, 87.44]	86.58 [85.91, 87.19]	86.58 [85.91, 87.19]
de_gsd-ud-test	gold	Lemmas	96.25 [95.95, 96.53]	96.64 [96.37, 96.92]	96.64 [96.37, 96.92]
de_gsd-ud-test	gold	UAS	87.01 [86.18, 87.75]	85.90 [84.99, 86.68]	87.09 [86.26, 87.84]
de_gsd-ud-test	gold	LAS	83.32 [82.43, 84.17]	82.17 [81.24, 83.02]	83.49 [82.59, 84.31]
de_gsd-ud-test	gold	CLAS	not measured	77.15 [76.03, 78.29]	78.67 [77.54, 79.74]
de_gsd-ud-test	gold	MLAS	not measured	58.17 [56.95, 59.56]	59.58 [58.38, 60.86]
de_gsd-ud-test	raw	Tokens	97.40 [97.09, 97.69]	97.40 [97.09, 97.69]	97.40 [97.09, 97.69]
de_gsd-ud-test	raw	Sentences	88.70 [86.70, 90.74]	88.63 [86.65, 90.56]	88.65 [86.73, 90.58]
de_gsd-ud-test	raw	Words	97.06 [96.70, 97.39]	97.06 [96.70, 97.39]	97.06 [96.70, 97.39]
de_gsd-ud-test	raw	UPOS	93.27 [92.79, 93.69]	93.33 [92.87, 93.75]	93.33 [92.87, 93.75]
de_gsd-ud-test	raw	XPOS	93.38 [92.91, 93.83]	93.35 [92.91, 93.79]	93.35 [92.91, 93.79]
de_gsd-ud-test	raw	AllTags	81.04 [80.35, 81.70]	81.69 [80.99, 82.33]	81.69 [80.99, 82.33]
de_gsd-ud-test	raw	UFeats	84.39 [83.77, 85.03]	85.16 [84.51, 85.74]	85.16 [84.51, 85.74]
de_gsd-ud-test	raw	Lemmas	93.36 [92.90, 93.78]	94.07 [93.64, 94.48]	94.07 [93.64, 94.48]
de_gsd-ud-test	raw	UAS	84.71 [83.86, 85.52]	84.31 [83.43, 85.14]	85.50 [84.64, 86.25]
de_gsd-ud-test	raw	LAS	81.17 [80.27, 82.00]	81.05 [80.15, 81.88]	82.38 [81.55, 83.18]
de_gsd-ud-test	raw	CLAS	not measured	79.72 [78.63, 80.79]	81.12 [80.13, 82.07]
de_gsd-ud-test	raw	MLAS	not measured	59.29 [58.13, 60.48]	60.36 [59.24, 61.44]
en_ewt-ud-test	gold	UPOS	96.58 [96.26, 96.86]	96.49 [96.19, 96.76]	96.49 [96.19, 96.76]
en_ewt-ud-test	gold	XPOS	96.02 [95.69, 96.32]	95.73 [95.40, 96.04]	95.73 [95.40, 96.04]
en_ewt-ud-test	gold	AllTags	93.66 [93.25, 94.02]	93.47 [93.07, 93.83]	93.47 [93.07, 93.83]
en_ewt-ud-test	gold	UFeats	96.44 [96.17, 96.69]	96.37 [96.09, 96.62]	96.37 [96.09, 96.62]
en_ewt-ud-test	gold	Lemmas	97.09 [96.81, 97.36]	97.26 [97.01, 97.52]	97.26 [97.01, 97.52]
en_ewt-ud-test	gold	UAS	88.56 [87.81, 89.26]	88.34 [87.65, 89.01]	88.34 [87.65, 89.01]
en_ewt-ud-test	gold	LAS	85.43 [84.61, 86.19]	85.12 [84.40, 85.87]	85.12 [84.40, 85.87]
en_ewt-ud-test	gold	CLAS	not measured	81.48 [80.57, 82.45]	81.48 [80.57, 82.45]
en_ewt-ud-test	gold	MLAS	not measured	75.10 [74.10, 76.11]	75.10 [74.10, 76.11]
en_ewt-ud-test	raw	Tokens	97.13 [96.83, 97.43]	97.13 [96.83, 97.43]	97.13 [96.83, 97.43]
en_ewt-ud-test	raw	Sentences	75.28 [73.54, 77.14]	75.85 [74.20, 77.60]	75.85 [74.20, 77.60]
en_ewt-ud-test	raw	Words	98.68 [98.45, 98.90]	98.68 [98.45, 98.90]	98.68 [98.45, 98.90]
en_ewt-ud-test	raw	UPOS	95.95 [95.59, 96.29]	95.95 [95.59, 96.27]	95.95 [95.59, 96.27]
en_ewt-ud-test	raw	XPOS	95.22 [94.83, 95.58]	95.18 [94.78, 95.54]	95.18 [94.78, 95.54]
en_ewt-ud-test	raw	AllTags	93.14 [92.69, 93.57]	93.39 [92.93, 93.80]	93.39 [92.93, 93.80]
en_ewt-ud-test	raw	UFeats	95.76 [95.42, 96.07]	95.94 [95.61, 96.27]	95.94 [95.61, 96.27]
en_ewt-ud-test	raw	Lemmas	96.14 [95.81, 96.48]	96.39 [96.04, 96.74]	96.39 [96.04, 96.74]
en_ewt-ud-test	raw	UAS	87.32 [86.58, 88.01]	88.78 [88.07, 89.47]	88.78 [88.07, 89.47]
en_ewt-ud-test	raw	LAS	85.02 [84.25, 85.77]	86.55 [85.82, 87.26]	86.55 [85.82, 87.26]
en_ewt-ud-test	raw	CLAS	not measured	83.38 [82.51, 84.30]	83.38 [82.51, 84.30]
en_ewt-ud-test	raw	MLAS	not measured	78.46 [77.50, 79.41]	78.46 [77.50, 79.41]
es_ancora-ud-test	gold	UPOS	98.10 [97.98, 98.24]	98.00 [97.87, 98.14]	98.00 [97.87, 98.14]
es_ancora-ud-test	gold	XPOS	84.88 [84.41, 85.31]	84.37 [83.90, 84.82]	84.37 [83.90, 84.82]
es_ancora-ud-test	gold	AllTags	83.67 [83.20, 84.13]	83.21 [82.74, 83.67]	83.21 [82.74, 83.67]
es_ancora-ud-test	gold	UFeats	96.50 [96.33, 96.66]	96.74 [96.58, 96.91]	96.74 [96.58, 96.91]
es_ancora-ud-test	gold	Lemmas	97.72 [97.58, 97.85]	98.53 [98.42, 98.64]	98.53 [98.42, 98.64]
es_ancora-ud-test	gold	UAS	88.14 [87.68, 88.63]	87.61 [87.18, 88.08]	89.50 [89.08, 89.94]
es_ancora-ud-test	gold	LAS	85.37 [84.89, 85.88]	84.66 [84.20, 85.15]	86.97 [86.51, 87.42]
es_ancora-ud-test	gold	CLAS	not measured	79.49 [78.89, 80.12]	82.53 [81.95, 83.14]
es_ancora-ud-test	gold	MLAS	not measured	72.39 [71.73, 73.14]	75.87 [75.23, 76.53]
es_ancora-ud-test	raw	Tokens	99.84 [99.76, 99.90]	99.84 [99.76, 99.90]	99.84 [99.76, 99.90]
es_ancora-ud-test	raw	Sentences	96.66 [95.79, 97.49]	96.54 [95.70, 97.31]	97.05 [96.24, 97.78]
es_ancora-ud-test	raw	Words	99.83 [99.75, 99.89]	99.83 [99.75, 99.89]	99.83 [99.75, 99.89]
es_ancora-ud-test	raw	UPOS	98.09 [97.96, 98.24]	98.20 [98.07, 98.34]	98.20 [98.07, 98.34]
es_ancora-ud-test	raw	XPOS	85.63 [85.17, 86.09]	85.87 [85.43, 86.33]	85.87 [85.43, 86.33]
es_ancora-ud-test	raw	AllTags	84.50 [84.05, 84.94]	84.84 [84.40, 85.29]	84.84 [84.40, 85.29]
es_ancora-ud-test	raw	UFeats	96.57 [96.40, 96.73]	96.83 [96.66, 96.99]	96.83 [96.66, 96.99]
es_ancora-ud-test	raw	Lemmas	97.75 [97.61, 97.89]	98.58 [98.46, 98.70]	98.58 [98.46, 98.70]
es_ancora-ud-test	raw	UAS	90.08 [89.60, 90.51]	90.92 [90.49, 91.33]	91.93 [91.49, 92.31]
es_ancora-ud-test	raw	LAS	87.42 [86.90, 87.92]	88.35 [87.88, 88.78]	89.70 [89.24, 90.11]
es_ancora-ud-test	raw	CLAS	not measured	84.50 [83.92, 85.06]	86.36 [85.78, 86.89]
es_ancora-ud-test	raw	MLAS	not measured	78.68 [78.03, 79.32]	80.63 [79.97, 81.23]
fr_gsd-ud-test	gold	UPOS	97.21 [96.82, 97.58]	96.99 [96.60, 97.39]	96.99 [96.60, 97.39]
fr_gsd-ud-test	gold	UFeats	96.24 [95.75, 96.67]	96.06 [95.58, 96.49]	96.06 [95.58, 96.49]
fr_gsd-ud-test	gold	Lemmas	97.56 [97.23, 97.88]	98.03 [97.72, 98.31]	98.03 [97.72, 98.31]
fr_gsd-ud-test	gold	UAS	89.36 [88.49, 90.23]	88.98 [88.06, 89.81]	89.52 [88.61, 90.43]
fr_gsd-ud-test	gold	LAS	86.55 [85.57, 87.49]	85.83 [84.90, 86.72]	86.89 [85.93, 87.88]
fr_gsd-ud-test	gold	CLAS	not measured	80.98 [79.72, 82.20]	82.47 [81.26, 83.85]
fr_gsd-ud-test	gold	MLAS	not measured	73.78 [72.25, 75.26]	75.00 [73.45, 76.63]
fr_gsd-ud-test	raw	Tokens	99.88 [99.79, 99.96]	99.88 [99.79, 99.96]	99.88 [99.79, 99.96]
fr_gsd-ud-test	raw	Sentences	92.40 [89.74, 94.66]	92.18 [89.49, 94.59]	92.65 [90.07, 94.98]
fr_gsd-ud-test	raw	Words	99.48 [99.29, 99.65]	99.48 [99.29, 99.65]	99.48 [99.29, 99.65]
fr_gsd-ud-test	raw	UPOS	97.06 [96.71, 97.42]	97.10 [96.71, 97.46]	97.10 [96.71, 97.46]
fr_gsd-ud-test	raw	UFeats	96.07 [95.59, 96.52]	96.26 [95.82, 96.68]	96.26 [95.82, 96.68]
fr_gsd-ud-test	raw	Lemmas	97.42 [97.09, 97.77]	97.96 [97.64, 98.25]	97.96 [97.64, 98.25]
fr_gsd-ud-test	raw	UAS	90.67 [89.74, 91.58]	91.34 [90.43, 92.18]	91.97 [91.12, 92.76]
fr_gsd-ud-test	raw	LAS	88.07 [87.07, 89.05]	88.96 [88.02, 89.84]	89.78 [88.84, 90.63]
fr_gsd-ud-test	raw	CLAS	not measured	85.67 [84.45, 86.80]	86.65 [85.41, 87.83]
fr_gsd-ud-test	raw	MLAS	not measured	79.66 [78.13, 81.14]	80.57 [79.06, 81.91]
it_markit-ud-test	gold	UPOS	95.69 [95.26, 96.12]	95.81 [95.39, 96.26]	95.81 [95.39, 96.26]
it_markit-ud-test	gold	XPOS	96.31 [95.90, 96.68]	96.26 [95.87, 96.66]	96.26 [95.87, 96.66]
it_markit-ud-test	gold	AllTags	89.51 [88.83, 90.21]	89.79 [89.12, 90.43]	89.79 [89.12, 90.43]
it_markit-ud-test	gold	UFeats	91.91 [91.27, 92.50]	92.12 [91.51, 92.73]	92.12 [91.51, 92.73]
it_markit-ud-test	gold	Lemmas	86.37 [85.60, 87.06]	86.38 [85.63, 87.08]	86.38 [85.63, 87.08]
it_markit-ud-test	gold	UAS	81.82 [80.77, 82.86]	82.05 [81.01, 83.15]	82.05 [81.01, 83.15]
it_markit-ud-test	gold	LAS	77.27 [76.19, 78.38]	77.63 [76.52, 78.78]	77.63 [76.52, 78.78]
it_markit-ud-test	gold	CLAS	not measured	72.13 [70.70, 73.64]	72.13 [70.70, 73.64]
it_markit-ud-test	gold	MLAS	not measured	57.58 [56.03, 59.25]	57.58 [56.03, 59.25]
it_markit-ud-test	raw	Tokens	99.93 [99.86, 99.98]	99.93 [99.86, 99.98]	99.93 [99.86, 99.98]
it_markit-ud-test	raw	Sentences	90.61 [87.84, 93.57]	90.11 [87.27, 92.93]	90.11 [87.27, 92.93]
it_markit-ud-test	raw	Words	99.73 [99.58, 99.86]	99.73 [99.58, 99.86]	99.73 [99.58, 99.86]
it_markit-ud-test	raw	UPOS	95.98 [95.54, 96.36]	96.12 [95.75, 96.52]	96.12 [95.75, 96.52]
it_markit-ud-test	raw	XPOS	96.56 [96.18, 96.92]	96.45 [96.05, 96.80]	96.45 [96.05, 96.80]
it_markit-ud-test	raw	AllTags	90.13 [89.50, 90.80]	90.50 [89.88, 91.10]	90.50 [89.88, 91.10]
it_markit-ud-test	raw	UFeats	92.40 [91.81, 93.01]	92.84 [92.29, 93.42]	92.84 [92.29, 93.42]
it_markit-ud-test	raw	Lemmas	86.46 [85.69, 87.17]	86.65 [85.93, 87.35]	86.65 [85.93, 87.35]
it_markit-ud-test	raw	UAS	85.40 [84.26, 86.44]	86.39 [85.36, 87.29]	86.39 [85.36, 87.29]
it_markit-ud-test	raw	LAS	81.12 [79.93, 82.18]	82.22 [81.04, 83.28]	82.22 [81.04, 83.28]
it_markit-ud-test	raw	CLAS	not measured	77.84 [76.30, 79.29]	77.84 [76.30, 79.29]
it_markit-ud-test	raw	MLAS	not measured	64.34 [62.76, 65.86]	64.34 [62.76, 65.86]
nl_alpino-ud-test	gold	UPOS	96.89 [96.24, 97.44]	96.91 [96.21, 97.44]	96.91 [96.21, 97.44]
nl_alpino-ud-test	gold	XPOS	95.09 [94.32, 95.77]	95.05 [94.26, 95.72]	95.05 [94.26, 95.72]
nl_alpino-ud-test	gold	AllTags	94.31 [93.48, 95.00]	94.13 [93.32, 94.87]	94.13 [93.32, 94.87]
nl_alpino-ud-test	gold	UFeats	96.73 [96.16, 97.22]	96.62 [96.06, 97.12]	96.62 [96.06, 97.12]
nl_alpino-ud-test	gold	Lemmas	91.88 [91.32, 92.47]	92.34 [91.80, 92.92]	92.34 [91.80, 92.92]
nl_alpino-ud-test	gold	UAS	90.41 [89.40, 91.32]	87.18 [86.11, 88.11]	90.23 [89.24, 91.11]
nl_alpino-ud-test	gold	LAS	87.63 [86.63, 88.59]	83.40 [82.24, 84.47]	87.24 [86.15, 88.24]
nl_alpino-ud-test	gold	CLAS	not measured	78.51 [77.05, 79.84]	82.88 [81.34, 84.21]
nl_alpino-ud-test	gold	MLAS	not measured	70.51 [68.69, 72.12]	76.21 [74.34, 77.73]
nl_alpino-ud-test	raw	Tokens	99.66 [99.46, 99.82]	99.66 [99.46, 99.82]	99.66 [99.46, 99.82]
nl_alpino-ud-test	raw	Sentences	94.81 [92.78, 96.42]	95.56 [94.03, 97.03]	95.90 [94.35, 97.34]
nl_alpino-ud-test	raw	Words	99.66 [99.46, 99.82]	99.66 [99.46, 99.82]	99.66 [99.46, 99.82]
nl_alpino-ud-test	raw	UPOS	96.66 [96.01, 97.23]	96.74 [96.11, 97.27]	96.74 [96.11, 97.27]
nl_alpino-ud-test	raw	XPOS	95.03 [94.32, 95.67]	95.27 [94.61, 95.94]	95.27 [94.61, 95.94]
nl_alpino-ud-test	raw	AllTags	94.31 [93.58, 95.01]	94.50 [93.79, 95.22]	94.50 [93.79, 95.22]
nl_alpino-ud-test	raw	UFeats	96.78 [96.26, 97.27]	96.80 [96.29, 97.28]	96.80 [96.29, 97.28]
nl_alpino-ud-test	raw	Lemmas	91.54 [90.97, 92.14]	92.05 [91.49, 92.67]	92.05 [91.49, 92.67]
nl_alpino-ud-test	raw	UAS	91.67 [90.65, 92.52]	91.93 [91.05, 92.69]	93.37 [92.55, 94.08]
nl_alpino-ud-test	raw	LAS	89.06 [87.93, 89.96]	89.09 [88.06, 89.97]	91.11 [90.20, 91.92]
nl_alpino-ud-test	raw	CLAS	not measured	85.23 [83.88, 86.40]	87.99 [86.70, 89.11]
nl_alpino-ud-test	raw	MLAS	not measured	79.56 [77.95, 81.03]	82.24 [80.73, 83.63]
pt_bosque-ud-test	gold	UPOS	96.56 [96.32, 96.80]	96.10 [95.82, 96.36]	96.10 [95.82, 96.36]
pt_bosque-ud-test	gold	UFeats	94.80 [94.49, 95.09]	94.48 [94.16, 94.80]	94.48 [94.16, 94.80]
pt_bosque-ud-test	gold	Lemmas	97.49 [97.30, 97.70]	97.59 [97.39, 97.79]	97.59 [97.39, 97.79]
pt_bosque-ud-test	gold	UAS	87.64 [87.07, 88.25]	85.88 [85.20, 86.50]	88.22 [87.63, 88.77]
pt_bosque-ud-test	gold	LAS	84.01 [83.39, 84.63]	81.83 [81.11, 82.53]	84.54 [83.90, 85.14]
pt_bosque-ud-test	gold	CLAS	not measured	77.38 [76.47, 78.25]	80.24 [79.51, 81.07]
pt_bosque-ud-test	gold	MLAS	not measured	67.49 [66.45, 68.46]	70.29 [69.36, 71.22]
pt_bosque-ud-test	raw	Tokens	99.86 [99.79, 99.92]	99.86 [99.79, 99.92]	99.86 [99.79, 99.92]
pt_bosque-ud-test	raw	Sentences	92.27 [90.68, 93.82]	92.57 [91.08, 93.99]	93.50 [92.14, 94.81]
pt_bosque-ud-test	raw	Words	99.26 [99.14, 99.38]	99.26 [99.14, 99.38]	99.26 [99.14, 99.38]
pt_bosque-ud-test	raw	UPOS	96.59 [96.32, 96.83]	96.75 [96.50, 96.98]	96.75 [96.50, 96.98]
pt_bosque-ud-test	raw	UFeats	95.06 [94.75, 95.34]	95.19 [94.90, 95.48]	95.19 [94.90, 95.48]
pt_bosque-ud-test	raw	Lemmas	96.96 [96.73, 97.19]	97.29 [97.09, 97.50]	97.29 [97.09, 97.50]
pt_bosque-ud-test	raw	UAS	89.38 [88.77, 89.91]	89.73 [89.18, 90.26]	90.68 [90.16, 91.19]
pt_bosque-ud-test	raw	LAS	86.47 [85.84, 87.04]	86.86 [86.27, 87.44]	87.98 [87.39, 88.55]
pt_bosque-ud-test	raw	CLAS	not measured	83.83 [83.04, 84.61]	85.27 [84.54, 85.99]
pt_bosque-ud-test	raw	MLAS	not measured	75.21 [74.33, 76.14]	76.55 [75.69, 77.41]
tr_boun-ud-test	gold	UPOS	91.50 [90.98, 92.05]	91.28 [90.72, 91.81]	91.28 [90.72, 91.81]
tr_boun-ud-test	gold	XPOS	not measured	44.67 [43.81, 45.55]	44.67 [43.81, 45.55]
tr_boun-ud-test	gold	AllTags	not measured	37.77 [37.03, 38.61]	37.77 [37.03, 38.61]
tr_boun-ud-test	gold	UFeats	80.57 [79.80, 81.33]	80.29 [79.54, 81.01]	80.29 [79.54, 81.01]
tr_boun-ud-test	gold	Lemmas	86.40 [85.75, 87.00]	86.00 [85.31, 86.61]	86.00 [85.31, 86.61]
tr_boun-ud-test	gold	UAS	75.25 [73.92, 76.56]	72.36 [70.98, 73.75]	74.44 [73.05, 75.76]
tr_boun-ud-test	gold	LAS	67.92 [66.56, 69.24]	64.97 [63.60, 66.26]	67.13 [65.67, 68.45]
tr_boun-ud-test	gold	CLAS	not measured	62.95 [61.49, 64.24]	65.35 [63.77, 66.74]
tr_boun-ud-test	gold	MLAS	not measured	43.83 [42.52, 45.02]	45.80 [44.46, 47.03]
tr_boun-ud-test	raw	Tokens	99.56 [99.41, 99.71]	99.56 [99.41, 99.71]	99.56 [99.41, 99.71]
tr_boun-ud-test	raw	Sentences	81.28 [78.81, 83.58]	79.89 [77.32, 82.20]	78.82 [76.14, 81.22]
tr_boun-ud-test	raw	Words	96.71 [96.34, 97.08]	96.71 [96.34, 97.08]	96.71 [96.34, 97.08]
tr_boun-ud-test	raw	UPOS	89.08 [88.46, 89.72]	88.62 [87.99, 89.32]	88.62 [87.99, 89.32]
tr_boun-ud-test	raw	XPOS	not measured	43.51 [42.62, 44.33]	43.51 [42.62, 44.33]
tr_boun-ud-test	raw	AllTags	not measured	37.44 [36.68, 38.26]	37.44 [36.68, 38.26]
tr_boun-ud-test	raw	UFeats	80.24 [79.44, 81.03]	80.23 [79.44, 81.03]	80.23 [79.44, 81.03]
tr_boun-ud-test	raw	Lemmas	84.51 [83.78, 85.20]	84.42 [83.71, 85.09]	84.42 [83.71, 85.09]
tr_boun-ud-test	raw	UAS	69.75 [68.39, 71.06]	69.30 [67.85, 70.58]	71.15 [69.82, 72.44]
tr_boun-ud-test	raw	LAS	63.03 [61.61, 64.41]	62.33 [60.88, 63.71]	64.31 [62.89, 65.78]
tr_boun-ud-test	raw	CLAS	not measured	61.35 [59.79, 62.70]	63.21 [61.68, 64.58]
tr_boun-ud-test	raw	MLAS	not measured	45.06 [43.56, 46.41]	46.89 [45.51, 48.21]
zh_gsdsimp-ud-test	gold	UPOS	88.77 [88.18, 89.35]	87.55 [86.92, 88.22]	87.55 [86.92, 88.22]
zh_gsdsimp-ud-test	gold	XPOS	87.86 [87.24, 88.47]	87.14 [86.47, 87.79]	87.14 [86.47, 87.79]
zh_gsdsimp-ud-test	gold	AllTags	85.15 [84.47, 85.82]	83.66 [82.95, 84.39]	83.66 [82.95, 84.39]
zh_gsdsimp-ud-test	gold	UFeats	96.03 [95.69, 96.39]	95.86 [95.48, 96.23]	95.86 [95.48, 96.23]
zh_gsdsimp-ud-test	gold	Lemmas	99.80 [99.71, 99.88]	99.78 [99.67, 99.86]	99.78 [99.67, 99.86]
zh_gsdsimp-ud-test	gold	UAS	69.15 [67.81, 70.55]	64.08 [62.81, 65.38]	67.22 [66.03, 68.48]
zh_gsdsimp-ud-test	gold	LAS	63.29 [61.88, 64.70]	57.55 [56.30, 58.83]	61.42 [60.21, 62.70]
zh_gsdsimp-ud-test	gold	CLAS	not measured	56.22 [54.82, 57.68]	59.72 [58.32, 61.19]
zh_gsdsimp-ud-test	gold	MLAS	not measured	44.42 [42.92, 45.86]	47.94 [46.40, 49.45]
zh_gsdsimp-ud-test	raw	Tokens	89.62 [88.81, 90.43]	89.62 [88.81, 90.43]	89.62 [88.81, 90.43]
zh_gsdsimp-ud-test	raw	Sentences	85.31 [82.10, 88.41]	83.64 [80.04, 86.90]	83.77 [80.32, 87.30]
zh_gsdsimp-ud-test	raw	Words	89.62 [88.81, 90.43]	89.62 [88.81, 90.43]	89.62 [88.81, 90.43]
zh_gsdsimp-ud-test	raw	UPOS	80.96 [80.07, 81.81]	80.66 [79.76, 81.48]	80.66 [79.76, 81.48]
zh_gsdsimp-ud-test	raw	XPOS	80.11 [79.28, 80.98]	79.75 [78.91, 80.63]	79.75 [78.91, 80.63]
zh_gsdsimp-ud-test	raw	AllTags	77.97 [77.04, 78.87]	77.47 [76.54, 78.38]	77.47 [76.54, 78.38]
zh_gsdsimp-ud-test	raw	UFeats	85.94 [85.11, 86.79]	85.98 [85.14, 86.82]	85.98 [85.14, 86.82]
zh_gsdsimp-ud-test	raw	Lemmas	89.45 [88.61, 90.27]	89.41 [88.61, 90.21]	89.41 [88.61, 90.21]
zh_gsdsimp-ud-test	raw	UAS	62.78 [61.24, 64.26]	62.91 [61.40, 64.43]	64.42 [62.89, 65.87]
zh_gsdsimp-ud-test	raw	LAS	58.84 [57.23, 60.35]	58.91 [57.38, 60.42]	60.98 [59.49, 62.45]
zh_gsdsimp-ud-test	raw	CLAS	not measured	55.70 [53.91, 57.39]	58.05 [56.40, 59.67]
zh_gsdsimp-ud-test	raw	MLAS	not measured	47.57 [45.78, 49.21]	49.33 [47.69, 50.97]

Paired recovery regression

Against the joint 84-language model, Turkish-BOUN raw sentence F1 changes from 79.89 to 78.82, difference -1.073 [-1.998, -0.134] (1,000 paired sentence resamples, seed 20261106). This is the only significantly negative difference among the 139 recomputed UD rows. Turkish raw LAS rises from 62.33 to 64.31, difference 1.978 [1.413, 2.578]. Selection was fixed to full-dev gold LAS before these test results; no test-driven reversion or additional training was performed.