Rankings / Mistral AI
Mistral Medium 3.5
open weightsreleased 2026-04-29
BenchAtlas Index
as of 2026-09-11
base configuration
rank #248
7 families · 4 categories · medium
high effort
rank #323
6 families · 3 categories · medium
Benchmark evidence
38 results
agentic coding
| τ²-Bench | 94.2 % | independent | Artificial Analysis | |
| τ²-Bench subset=banking | 15.1 % | independent | Artificial Analysis |
coding
| SciCode | 40.2 % | independent | Artificial Analysis |
external indices
| AA Coding Index | 46.9 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 14.9 points | independent | Artificial Analysis | |
| Vals Index | high effort | 17.9 points | independent | Vals AI |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1478.7 1467.5–1489.9 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1470.2 1460.7–1479.8 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1458.1 1447.7–1468.5 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1448.3 1421.8–1474.9 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1445.5 1437.7–1453.4 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1444.3 1435.7–1453.0 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1440.3 1416.3–1464.2 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1438.2 1420.3–1456.1 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1438.1 1416.8–1459.4 | 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 | 1433.6 1419.2–1448.0 | 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 | 1431.2 1418.1–1444.4 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1431.2 1416.8–1445.6 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1430.7 1421.3–1440.2 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1429.8 1404.9–1454.6 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1426.9 1420.3–1433.4 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1422.8 1400.9–1444.5 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1422.4 1412.0–1432.7 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1421.1 1412.4–1429.8 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1415.8 1398.0–1433.6 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1406.8 1398.4–1415.1 | 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 | 1406.1 1394.3–1417.8 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1397.1 1382.7–1411.5 | 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 | 1396.9 1384.4–1409.4 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 74.8 % | independent | Artificial Analysis | |
| GPQA Diamond implementation=vals-ai | high effort | 34.8 % | independent | Vals AI |
| Humanity's Last Exam implementation=artificial-analysis | 13.8 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=vals-ai | high effort | 75.3 % | independent | Vals AI |
long context instruction
| AA-LCR | 69.3 % | independent | Artificial Analysis | |
| IFBench | 68.8 % | independent | Artificial Analysis |
professional
| CaseLaw | high effort | 44.2 % | independent | Vals AI |
| CorpFin | high effort | 58.8 % | independent | Vals AI |
| TaxEval | high effort | 68.0 % | independent | Vals AI |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Mistral Medium 3.5 | Terminal-Bench 2.1 | 50.6 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Mistral Medium 3.5 | Terminal-Bench Hard | 33.3 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.