Rankings / Mistral AI
Mistral Medium 2505
released 2025-05-07
BenchAtlas Index
as of 2026-09-11
Benchmark evidence
41 results
external indices
| ECI | 134.1 points | independent | Epoch AI Benchmarking Hub |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1433.0 1425.0–1441.0 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1422.0 1415.4–1428.5 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1418.7 1404.9–1432.4 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1409.6 1401.8–1417.4 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1409.4 1396.5–1422.3 | community | LMArena Leaderboard Dataset | |
| Industry Life And Physical And Social Science (style control)older version arena=text · category=industry_life_and_physical_and_social_science · style_control=true | 1408.8 1400.4–1417.2 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1403.3 1395.0–1411.5 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1402.4 1396.5–1408.4 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1400.6 1394.6–1406.6 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1392.9 1374.1–1411.7 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1391.7 1383.7–1399.8 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1391.5 1379.8–1403.3 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1387.3 1382.6–1392.1 | community | LMArena Leaderboard Dataset | |
| Industry Business And Management And Financial Operations (style control)older version arena=text · category=industry_business_and_management_and_financial_operations · style_control=true | 1387.0 1378.2–1395.7 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1386.0 1372.9–1399.2 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1384.4 1373.4–1395.4 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1379.6 1354.1–1405.1 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1378.7 1365.0–1392.4 | community | LMArena Leaderboard Dataset | |
| Industry Writing And Literature And Language (style control)older version arena=text · category=industry_writing_and_literature_and_language · style_control=true | 1369.8 1362.2–1377.4 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1369.4 1363.8–1375.0 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1366.1 1359.6–1372.5 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1366.0 1358.8–1373.1 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1363.7 1354.1–1373.4 | community | LMArena Leaderboard Dataset | |
| Industry Entertainment And Sports And Media (style control)older version arena=text · category=industry_entertainment_and_sports_and_media · style_control=true | 1354.7 1346.4–1362.9 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1353.6 1341.2–1366.0 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1347.8 1335.6–1359.9 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1326.1 1306.0–1346.2 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1316.2 1292.3–1340.2 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond | 59.5 % | independent | Epoch AI Benchmarking Hub 2025-05-07 | |
| MMLU-Pro implementation=vals-ai | 75.3 % | independent | Vals AI |
multimodal
| MMMU implementation=vals-ai | 63.0 % | independent | Vals AI |
professional
| CorpFin | 50.7 % | independent | Vals AI | |
| LegalBench | 62.0 % | independent | Vals AI | |
| MedQA | 78.2 % | independent | Vals AI | |
| TaxEval | 70.3 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | 42.3 % | independent | Vals AI | |
| FrontierMath | 0.3 % | independent | Epoch AI Benchmarking Hub 2025-05-07 | |
| MATH-500 implementation=vals-ai | 87.0 % | independent | Vals AI | |
| MATH Level 5 | 81.6 % | independent | Epoch AI Benchmarking Hub 2025-05-07 | |
| OTIS Mock AIME 2024–2025 | 32.2 % | independent | Epoch AI Benchmarking Hub 2025-05-07 |
