Benchmark Almanac

SIGMORPHON 2023 Shared Task on Interlinear Glossing

Tü-CL_2 76.6% tops its leaderboard
Not in model cards

Models label each word’s meaningful parts with translations or grammatical tags. The organizers rank submissions by word-level accuracy pooled across languages.

The published rankings use the original data. The organizers removed duplicates on May 16, 2026, so scores on the revised data require a separate comparison.

Made by
SIGMORPHON
Released
February 2023
Kind
Translation
Level
Expert
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
Many languages
In and out
Text → Text
Interaction
Single turn
Run by
Anyone
In views
Many languages
12
Entries on its own leaderboard, 0 models we track

Tü-CL_2 tops the leaderboard with 76.6%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 1 Tü-CL_2 Track 2 76.6%
  2. 2 Tü-CL_1 Track 2 74.4%
  3. 3 SigMoreFun_2 Track 2 73.4%
  4. 4 LISNTeam_1 Track 2 (partial submission) 72.4%
  5. 5 SigMoreFun_1 Track 2 71.3%
  6. 6 SigMoreFun_4 Track 2 69.1%
  7. 7 LISNTeam_2 Track 2 (partial submission) 67.8%
  8. 8 TeamSiggyMorph_2 Track 2 61.1%
  9. 9 COATES_1 Track 1 59.5%
  10. 10 BASELINE Track 2 59.1%
  11. 11 SigMoreFun_3 Track 2 53.4%
  12. 12 TeamSiggyMorph_1 Track 1 (partial submission) 46.7%

Source: Official SIGMORPHON 2023 Shared Task on Interlinear Glossing leaderboard

#EntryScoreSettingDateSource
1 Tü-CL_2 76.6% Track 2 Official leaderboard
2 Tü-CL_1 74.4% Track 2 Official leaderboard
3 SigMoreFun_2 73.4% Track 2 Official leaderboard
4 LISNTeam_1 72.4% Track 2 (partial submission) Official leaderboard
5 SigMoreFun_1 71.3% Track 2 Official leaderboard
6 SigMoreFun_4 69.1% Track 2 Official leaderboard
7 LISNTeam_2 67.8% Track 2 (partial submission) Official leaderboard
8 TeamSiggyMorph_2 61.1% Track 2 Official leaderboard
9 COATES_1 59.5% Track 1 Official leaderboard
10 BASELINE 59.1% Track 2 Official leaderboard
11 SigMoreFun_3 53.4% Track 2 Official leaderboard
12 TeamSiggyMorph_1 46.7% Track 1 (partial submission) Official leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Multilingual

All 545 in Multilingual
  • MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
  • WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET. K-EXAONE 90.5%
  • MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language. Qwen3.7-Max 87%
  • CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories. Solar Open 2 90.7%
  • Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
  • MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (12 entries).
  • Pass Models scored 12 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 12 entries at the last read, none a model we track.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check