SportsEval
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
- Subject
- Languages and literature
- Interaction
- Single turn
- Items from
- Real work and use, Written by experts
- 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
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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 90.0
Gemini 2.5 Pro
- 82.2 Shy
- 81.6 Erlendur
- 79.4 GPT-4.1
- 73.6 TranssionTranslate
- 72.4 ONLINE-B
- 70.8 TowerPlus-9B
- 70.2 hybrid
- 62.2 ONLINE-G
- 61.9 Claude-4
- 61.0 AMI
- 55.0
Gemma 3 27B
- 54.1
Llama 4 Maverick
- 47.6 NLLB
- 45.6
Mistral Medium
- 44.4 GemTrans
- 41.1 SalamandraTA
- 39.8
Gemma 3 12B
- 39.5 IRB-MT
- 30.7 CommandA-MT
- 28.6
DeepSeek-V3
- 24.0 Qwen3-235B
- 23.0 CommandA
- 20.8
Llama 3.1-8B
- 18.0 TowerPlus-72B
- 9.48 UvA-MT
- 6.00
Mistral 7B v0.1
- 6.00
Qwen2.5-7B
- 5.30
Aya Expanse 32B
- 3.77 EuroLLM-22B
- 2.37
Command R7B
- 2.23
Aya Expanse 8B
- 1.95 IR-MultiagentMT
- 1.81 EuroLLM-9B
- 1
Gemini 2.5 Pro Jun 2025 90%
- 2 Shy 82.2%
- 3 Erlendur 81.6%
- 4 GPT-4.1 79.4%
- 5 TranssionTranslate 73.6%
- 6 ONLINE-B 72.4%
- 7 TowerPlus-9B 70.8%
- 8 hybrid 70.2%
- 9 ONLINE-G 62.2%
- 10 Claude-4 61.9%
- 11 AMI 61%
- 12
Gemma 3 27B 55%
- 13
Llama 4 Maverick 54.1%
- 14 NLLB 47.6%
- 15
Mistral Medium 45.6%
- 16 GemTrans 44.4%
- 17 SalamandraTA 41.1%
- 18
Gemma 3 12B 39.8%
- 19 IRB-MT 39.5%
- 20 CommandA-MT 30.7%
- 21
DeepSeek-V3 Mar 2025 28.6%
- 22 Qwen3-235B 24%
- 23 CommandA 23%
- 24
Llama 3.1-8B 20.8%
- 25 TowerPlus-72B 18%
- 26 UvA-MT 9.48%
- 27
Mistral 7B v0.1 6.00%
- 28
Qwen2.5-7B 6.00%
- 29
Aya Expanse 32B 5.30%
- 30 EuroLLM-22B 3.77%
- 31
Command R7B 2.37%
- 32
Aya Expanse 8B 2.23%
- 33 IR-MultiagentMT 1.95%
- 34 EuroLLM-9B 1.81%
Source: Official SportsEval leaderboard
- 1
Gemini 2.5 Pro Jun 2025 90%
- 2 GPT-4.1 79.4%
- 3
Gemma 3 27B 55%
- 4
Llama 4 Maverick 54.1%
- 5
Mistral Medium 45.6%
- 6
Gemma 3 12B 39.8%
- 7
DeepSeek-V3 Mar 2025 28.6%
- 8
Llama 3.1-8B 20.8%
- 9
Mistral 7B v0.1 6.00%
- 10
Qwen2.5-7B 6.00%
- 11
Aya Expanse 32B 5.30%
- 12
Command R7B 2.37%
- 13
Aya Expanse 8B 2.23%
Source: Official SportsEval leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 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 | | 55% | Mar 2025 | Official leaderboard | |
| 13 | | 54.1% | Apr 2025 | Official leaderboard | |
| 14 | NLLB | 47.6% | Official leaderboard | ||
| 15 | | 45.6% | Dec 2023 | Official leaderboard | |
| 16 | GemTrans | 44.4% | Official leaderboard | ||
| 17 | SalamandraTA | 41.1% | Official leaderboard | ||
| 18 | | 39.8% | Mar 2025 | Official leaderboard | |
| 19 | IRB-MT | 39.5% | Official leaderboard | ||
| 20 | CommandA-MT | 30.7% | Official leaderboard | ||
| 21 | | 28.6% | Mar 2025 | Official leaderboard | |
| 22 | Qwen3-235B | 24% | Official leaderboard | ||
| 23 | CommandA | 23% | Official leaderboard | ||
| 24 | | 20.8% | Jul 2024 | Official leaderboard | |
| 25 | TowerPlus-72B | 18% | Official leaderboard | ||
| 26 | UvA-MT | 9.48% | Official leaderboard | ||
| 27 | | 6.00% | Sep 2023 | Official leaderboard | |
| 28 | | 6.00% | Sep 2024 | Official leaderboard | |
| 29 | | 5.30% | Oct 2024 | Official leaderboard | |
| 30 | EuroLLM-22B | 3.77% | Official leaderboard | ||
| 31 | | 2.37% | Dec 2024 | Official leaderboard | |
| 32 | | 2.23% | Oct 2024 | Official leaderboard | |
| 33 | IR-MultiagentMT | 1.95% | Official leaderboard | ||
| 34 | EuroLLM-9B | 1.81% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 90% | Jun 2025 | Official leaderboard | |
| 2 | GPT-4.1 | 79.4% | Apr 2025 | Official leaderboard | |
| 3 | | 55% | Mar 2025 | Official leaderboard | |
| 4 | | 54.1% | Apr 2025 | Official leaderboard | |
| 5 | | 45.6% | Dec 2023 | Official leaderboard | |
| 6 | | 39.8% | Mar 2025 | Official leaderboard | |
| 7 | | 28.6% | Mar 2025 | Official leaderboard | |
| 8 | | 20.8% | Jul 2024 | Official leaderboard | |
| 9 | | 6.00% | Sep 2023 | Official leaderboard | |
| 10 | | 6.00% | Sep 2024 | Official leaderboard | |
| 11 | | 5.30% | Oct 2024 | Official leaderboard | |
| 12 | | 2.37% | Dec 2024 | Official leaderboard | |
| 13 | | 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
Gemini 2.5 Pro Jun 2025 78.9%
- 2 GPT-4.1 53.5%
- 3
Llama 4 Maverick ↑1 38%
- 4
DeepSeek-V3 Mar 2025 ↑3 28.2%
- 5
Mistral Medium 23.9%
- 6
Gemma 3 27B ↓3 22.5%
- 7
Gemma 3 12B ↓1 9.86%
- 8
Llama 3.1-8B 4.23%
- 9
Aya Expanse 32B ↑2 4.23%
- 10
Mistral 7B v0.1 ↓1 0%
Basketball terms
13 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 91.7%
- 2 GPT-4.1 84.7%
- 3
Llama 4 Maverick ↑1 63.9%
- 4
Gemma 3 27B ↓1 61.8%
- 5
Mistral Medium 50.2%
- 6
Gemma 3 12B 48.5%
- 7
Llama 3.1-8B ↑1 23.2%
- 8
DeepSeek-V3 Mar 2025 ↓1 14.9%
- 9
Aya Expanse 32B ↑2 8.30%
- 10
Mistral 7B v0.1 ↓1 7.88%
Golf terms
13 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 91.8%
- 2 GPT-4.1 82%
- 3
Gemma 3 27B 55.7%
- 4
Llama 4 Maverick 44.3%
- 5
Mistral Medium 42.6%
- 6
DeepSeek-V3 Mar 2025 ↑1 41%
- 7
Gemma 3 12B ↓1 34.4%
- 8
Llama 3.1-8B 13.1%
- 9
Aya Expanse 32B ↑2 9.84%
- 10
Mistral 7B v0.1 ↓1 8.20%
Gymnastics terms
13 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 80.4%
- 2 GPT-4.1 50%
- 3
Gemma 3 27B 19.6%
- 4
DeepSeek-V3 Mar 2025 ↑3 16.1%
- 5
Mistral Medium 14.3%
- 6
Llama 4 Maverick ↓2 12.5%
- 7
Gemma 3 12B ↓1 8.93%
- 8
Qwen2.5-7B ↑2 5.36%
- 9
Aya Expanse 32B ↑2 1.79%
- 10
Mistral 7B v0.1 ↓1 0%
Football terms
13 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 92.7%
- 2 GPT-4.1 86.5%
- 3
Gemma 3 27B 63.9%
- 4
Llama 4 Maverick 60.1%
- 5
Mistral Medium 53.8%
- 6
Gemma 3 12B 46.9%
- 7
DeepSeek-V3 Mar 2025 39.9%
- 8
Llama 3.1-8B 28.5%
- 9
Mistral 7B v0.1 6.60%
- 10
Qwen2.5-7B 6.60%
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.
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.
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
- 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.