Rankings / Mistral AI
Mistral Medium 3.5
open weightsreleased 2026-04-29
BenchAtlas Index
as of 2026-07-14
base configuration
rank #237
7 families · 4 categories · medium
high effort
rank #309
6 families · 3 categories · medium
Benchmark evidence
37 results
agentic coding
| τ²-Bench | 94.2 % | independent | Artificial Analysis | |
| τ²-Bench subset=banking | 14.4 % | independent | Artificial Analysis |
coding
| SciCode | 39.6 % | independent | Artificial Analysis |
external indices
| AA Coding Index | 46.9 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 29.9 points | independent | Artificial Analysis | |
| Vals Index | high effort | 37.8 points | independent | Vals AI |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1478.9 1467.7–1490.1 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1470.0 1460.4–1479.6 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1457.0 1446.6–1467.4 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1445.1 1437.2–1453.0 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1444.8 1436.1–1453.5 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1442.8 1418.6–1467.1 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1440.0 1421.7–1458.2 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1437.1 1415.8–1458.4 | 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 | 1433.4 1418.9–1447.9 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1432.7 1407.9–1457.5 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1431.6 1417.1–1446.1 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1431.0 1421.4–1440.5 | 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 | 1430.4 1417.1–1443.7 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1427.2 1420.6–1433.8 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1424.7 1402.8–1446.5 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1421.3 1412.5–1430.0 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1421.1 1410.7–1431.5 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1416.5 1398.7–1434.2 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1406.9 1398.5–1415.3 | 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 | 1403.0 1391.1–1414.8 | 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 | 1396.5 1383.9–1409.0 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1393.9 1379.5–1408.4 | 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 | 12.8 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=vals-ai | high effort | 75.3 % | independent | Vals AI |
long context instruction
| AA-LCR | 61.0 % | 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.