Benchmark Almanac

SportsEval

Gemini 2.5 Pro Jun 2025 90% leads since June 2025
Not in model cards

Models translate 300 English passages about five sports into Icelandic. The scorer checks the Icelandic terms. Humans also judged 37 passages per system at WMT25.

Passes test 2. The makers publish scores for 34 systems, including Gemini, Claude, GPT, Gemma and Qwen. The 2026 revision rescored the original translations with an expanded list of accepted forms.

Released
June 2025
Kind
Translation
Level
University
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English, Icelandic
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Gemini 2.5 Pro Jun 2025 #97 on the capability index
Last model added
June 2025
Scores refreshed
November 20th, 2026
34
Entries on its own leaderboard, 13 models we track

Gemini 2.5 Pro leads with 90% among models released by June 2025 Gemini 2.5 Pro leads with 90% among models released by June 2025

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. 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 90%
  2. 2 Shy 82.2%
  3. 3 Erlendur 81.6%
  4. 4 GPT-4.1 79.4%
  5. 5 TranssionTranslate 73.6%
  6. 6 ONLINE-B 72.4%
  7. 7 TowerPlus-9B 70.8%
  8. 8 hybrid 70.2%
  9. 9 ONLINE-G 62.2%
  10. 10 Claude-4 61.9%
  11. 11 AMI 61%
  12. 12 Gemma 3 27B 55%
  13. 13 Llama 4 Maverick 54.1%
  14. 14 NLLB 47.6%
  15. 15 Mistral Medium 45.6%
  16. 16 GemTrans 44.4%
  17. 17 SalamandraTA 41.1%
  18. 18 Gemma 3 12B 39.8%
  19. 19 IRB-MT 39.5%
  20. 20 CommandA-MT 30.7%
  21. 21 DeepSeek-V3 Mar 2025 28.6%
  22. 22 Qwen3-235B 24%
  23. 23 CommandA 23%
  24. 24 Llama 3.1-8B 20.8%
  25. 25 TowerPlus-72B 18%
  26. 26 UvA-MT 9.48%
  27. 27 Mistral 7B v0.1 6.00%
  28. 28 Qwen2.5-7B 6.00%
  29. 29 Aya Expanse 32B 5.30%
  30. 30 EuroLLM-22B 3.77%
  31. 31 Command R7B 2.37%
  32. 32 Aya Expanse 8B 2.23%
  33. 33 IR-MultiagentMT 1.95%
  34. 34 EuroLLM-9B 1.81%

Source: Official SportsEval leaderboard

#EntryScoreSettingDateSource
1 Gemini 2.5 Pro Jun 2025 90% Jun 2025 Official leaderboard
2 Shy 82.2% Official leaderboard
3 Erlendur 81.6% Official leaderboard
4 GPT-4.1 79.4% Apr 2025 Official leaderboard
5 TranssionTranslate 73.6% Official leaderboard
6 ONLINE-B 72.4% Official leaderboard
7 TowerPlus-9B 70.8% Official leaderboard
8 hybrid 70.2% Official leaderboard
9 ONLINE-G 62.2% Official leaderboard
10 Claude-4 61.9% Official leaderboard
11 AMI 61% Official leaderboard
12 Gemma 3 27B 55% Mar 2025 Official leaderboard
13 Llama 4 Maverick 54.1% Apr 2025 Official leaderboard
14 NLLB 47.6% Official leaderboard
15 Mistral Medium 45.6% Dec 2023 Official leaderboard
16 GemTrans 44.4% Official leaderboard
17 SalamandraTA 41.1% Official leaderboard
18 Gemma 3 12B 39.8% Mar 2025 Official leaderboard
19 IRB-MT 39.5% Official leaderboard
20 CommandA-MT 30.7% Official leaderboard
21 DeepSeek-V3 Mar 2025 28.6% Mar 2025 Official leaderboard
22 Qwen3-235B 24% Official leaderboard
23 CommandA 23% Official leaderboard
24 Llama 3.1-8B 20.8% Jul 2024 Official leaderboard
25 TowerPlus-72B 18% Official leaderboard
26 UvA-MT 9.48% Official leaderboard
27 Mistral 7B v0.1 6.00% Sep 2023 Official leaderboard
28 Qwen2.5-7B 6.00% Sep 2024 Official leaderboard
29 Aya Expanse 32B 5.30% Oct 2024 Official leaderboard
30 EuroLLM-22B 3.77% Official leaderboard
31 Command R7B 2.37% Dec 2024 Official leaderboard
32 Aya Expanse 8B 2.23% Oct 2024 Official leaderboard
33 IR-MultiagentMT 1.95% Official leaderboard
34 EuroLLM-9B 1.81% Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 2.5 Pro Jun 2025 90% Jun 2025 Official leaderboard
2 GPT-4.1 79.4% Apr 2025 Official leaderboard
3 Gemma 3 27B 55% Mar 2025 Official leaderboard
4 Llama 4 Maverick 54.1% Apr 2025 Official leaderboard
5 Mistral Medium 45.6% Dec 2023 Official leaderboard
6 Gemma 3 12B 39.8% Mar 2025 Official leaderboard
7 DeepSeek-V3 Mar 2025 28.6% Mar 2025 Official leaderboard
8 Llama 3.1-8B 20.8% Jul 2024 Official leaderboard
9 Mistral 7B v0.1 6.00% Sep 2023 Official leaderboard
10 Qwen2.5-7B 6.00% Sep 2024 Official leaderboard
11 Aya Expanse 32B 5.30% Oct 2024 Official leaderboard
12 Command R7B 2.37% Dec 2024 Official leaderboard
13 Aya Expanse 8B 2.23% Oct 2024 Official leaderboard

Rankings by part

We read 5 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Chess terms, Basketball terms and Golf terms. Gemini 2.5 Pro leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

Chess terms

13 models we track have a score here.

  1. 1 Gemini 2.5 Pro Jun 2025 78.9%
  2. 2 GPT-4.1 53.5%
  3. 3 Llama 4 Maverick ↑1 38%
  4. 4 DeepSeek-V3 Mar 2025 ↑3 28.2%
  5. 5 Mistral Medium 23.9%
  6. 6 Gemma 3 27B ↓3 22.5%
  7. 7 Gemma 3 12B ↓1 9.86%
  8. 8 Llama 3.1-8B 4.23%
  9. 9 Aya Expanse 32B ↑2 4.23%
  10. 10 Mistral 7B v0.1 ↓1 0%

2 models have held number one on the official leaderboard since its release in June 2025

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

OpenAI Google DeepMind
Own leaderboard Passed 85% in Jun 2025, by Gemini 2.5 Pro

Source: Official SportsEval leaderboard

Gemini 2.5 Pro on the official leaderboard passed 85% in June 2025

Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2024 2025 Near the ceiling (85%) Gemini 2.5 Pro GPT-4.1 Gemma 3 27B Mistral Medium Mistral 7B v0.1 0% 20% 40% 60% 80% 100% 2024 2025 Near the ceiling (85%) Gemini 2.5 Pro GPT-4.1

Source: Official SportsEval 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 (34 entries).
  • Pass Models scored 13 models we track, plus 21 other entries on its leaderboard.
  • Note Newest score The newest came 17 months ago, in June 2025, for Gemini 2.5 Pro. That’s expected for a saturated test.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Gemini 2.5 Pro (#97).
  • Note Headroom Saturated. The best is 90%, past 85% since June 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 13 rows for models we track and 21 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