Benchmark Almanac

IITP-Legal

Gemini 2.5 Pro Jun 2025 33.4 leads since June 2025
Not in model cards

Models translate 5,000 English legal sentences into Hindi. The suite includes 100 sentences at each length from five through 54 words. The original ranking uses BLEU.

Passes tests 2 and 4. The organizers ranked 37 systems. Vaquill independently tested a fixed 500-sentence subset and published all outputs. Two experts also evaluated the top 20 original systems.

Released
June 2025
Kind
Translation
Level
University
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English, Hindi
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Law and finance
Strongest model tested
Gemini 2.5 Pro Jun 2025 #97 on the capability index
Last model added
June 2025
Scores refreshed
November 20th, 2026
37
Entries in its paper, 13 models we track

Gemini 2.5 Pro leads with 33.4 among models released by June 2025 Gemini 2.5 Pro leads with 33.4 among models released by June 2025

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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. This view shows only models we track, each at its best.

The newest model with a score here came out in June 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Gemini 2.5 Pro Jun 2025 33.4
  2. 2 ONLINE-B 31.8
  3. 3 TranssionTranslate 31.6
  4. 4 ONLINE-G 31.2
  5. 5 Claude-4 31.1
  6. 6 Llama 4 Maverick 28.5
  7. 7 NLLB 27.9
  8. 8 hybrid 27.0
  9. 9 DeepSeek-V3 Mar 2025 26.6
  10. 10 GPT-4.1 26.0
  11. 11 TowerPlus-9B 25.8
  12. 12 HYT 25.6
  13. 13 Shy 25.6
  14. 14 TMTHY 25.6
  15. 15 CommandA 24.2
  16. 16 Gemma 3 27B 23.8
  17. 17 TowerPlus-72B 23.5
  18. 18 Mistral Medium 23.3
  19. 19 Qwen3-235B 22.9
  20. 20 EuroLLM-22B 22.2
  21. 21 EuroLLM-9B 21.5
  22. 22 Gemma 3 12B 21.5
  23. 23 IR-MultiagentMT 21.4
  24. 24 CommandA-MT 21.1
  25. 25 Aya Expanse 32B 20.5
  26. 26 UvA-MT 19.8
  27. 27 IRB-MT 17.3
  28. 28 Aya Expanse 8B 16.7
  29. 29 Llama 3.1-8B 15.2
  30. 30 GemTrans 15.2
  31. 31 Command R7B 12.4
  32. 32 Qwen2.5-7B 8.75
  33. 33 Mistral 7B v0.1 3.03
  34. 34 Algharb 2.68
  35. 35 MMMT 2.68
  36. 36 Wenyiil 2.68
  37. 37 Yolu 2.68

Source: The IITP-Legal paper

#EntryScoreSettingDateSource
1 Gemini 2.5 Pro Jun 2025 33.4 Jun 2025 Official leaderboard
2 ONLINE-B 31.8 Official leaderboard
3 TranssionTranslate 31.6 Official leaderboard
4 ONLINE-G 31.2 Official leaderboard
5 Claude-4 31.1 Official leaderboard
6 Llama 4 Maverick 28.5 Apr 2025 Official leaderboard
7 NLLB 27.9 Official leaderboard
8 hybrid 27.0 Official leaderboard
9 DeepSeek-V3 Mar 2025 26.6 Mar 2025 Official leaderboard
10 GPT-4.1 26.0 Apr 2025 Official leaderboard
11 TowerPlus-9B 25.8 Official leaderboard
12 HYT 25.6 Official leaderboard
13 Shy 25.6 Official leaderboard
14 TMTHY 25.6 Official leaderboard
15 CommandA 24.2 Official leaderboard
16 Gemma 3 27B 23.8 Mar 2025 Official leaderboard
17 TowerPlus-72B 23.5 Official leaderboard
18 Mistral Medium 23.3 Dec 2023 Official leaderboard
19 Qwen3-235B 22.9 Official leaderboard
20 EuroLLM-22B 22.2 Official leaderboard
21 EuroLLM-9B 21.5 Official leaderboard
22 Gemma 3 12B 21.5 Mar 2025 Official leaderboard
23 IR-MultiagentMT 21.4 Official leaderboard
24 CommandA-MT 21.1 Official leaderboard
25 Aya Expanse 32B 20.5 Oct 2024 Official leaderboard
26 UvA-MT 19.8 Official leaderboard
27 IRB-MT 17.3 Official leaderboard
28 Aya Expanse 8B 16.7 Oct 2024 Official leaderboard
29 Llama 3.1-8B 15.2 Jul 2024 Official leaderboard
30 GemTrans 15.2 Official leaderboard
31 Command R7B 12.4 Dec 2024 Official leaderboard
32 Qwen2.5-7B 8.75 Sep 2024 Official leaderboard
33 Mistral 7B v0.1 3.03 Sep 2023 Official leaderboard
34 Algharb 2.68 Official leaderboard
35 MMMT 2.68 Official leaderboard
36 Wenyiil 2.68 Official leaderboard
37 Yolu 2.68 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 2.5 Pro Jun 2025 33.4 Jun 2025 Official leaderboard
2 Llama 4 Maverick 28.5 Apr 2025 Official leaderboard
3 DeepSeek-V3 Mar 2025 26.6 Mar 2025 Official leaderboard
4 GPT-4.1 26.0 Apr 2025 Official leaderboard
5 Gemma 3 27B 23.8 Mar 2025 Official leaderboard
6 Mistral Medium 23.3 Dec 2023 Official leaderboard
7 Gemma 3 12B 21.5 Mar 2025 Official leaderboard
8 Aya Expanse 32B 20.5 Oct 2024 Official leaderboard
9 Aya Expanse 8B 16.7 Oct 2024 Official leaderboard
10 Llama 3.1-8B 15.2 Jul 2024 Official leaderboard
11 Command R7B 12.4 Dec 2024 Official leaderboard
12 Qwen2.5-7B 8.75 Sep 2024 Official leaderboard
13 Mistral 7B v0.1 3.03 Sep 2023 Official leaderboard

2 models have held number one in the benchmark’s paper since its release in June 2025

Lab claims count from the day the card came out, independent runs from the model’s release.

Meta Google DeepMind
Benchmark paper Not tested since Jun 2025

Source: The IITP-Legal paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper
0.00 10.0 20.0 30.0 40.0 2024 2025 0.00 10.0 20.0 30.0 40.0 2024 2025

Source: Official IITP-Legal 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 17 months ago, in June 2025, for Gemini 2.5 Pro. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (37 entries).
  • Pass Models scored 13 models we track, plus 24 other entries on its leaderboard.
  • Warning Newest score The newest came 17 months ago, in June 2025, for Gemini 2.5 Pro.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.5 Pro (#97).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on aclanthology.org: 13 rows for models we track and 24 other entries at the last read.
  • 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