Rankings / Mistral AI
Mistral Large 3
open weightsreleased 2025-12-02
BenchAtlas Index
as of 2026-07-14
base configuration
rank #383
9 families · 5 categories · high
Benchmark evidence
41 results
agentic coding
| τ²-Bench | 24.6 % | independent | Artificial Analysis | |
| τ²-Bench subset=banking | 5.8 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | 46.5 % | independent | Artificial Analysis | |
| SciCode | 36.2 % | independent | Artificial Analysis |
external indices
| AA Coding Index | 20.1 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 15.9 points | independent | Artificial Analysis | |
| AA Math Index | 38.0 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1466.3 1460.1–1472.4 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1454.1 1448.9–1459.3 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1448.2 1429.2–1467.3 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1440.6 1434.8–1446.4 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1435.1 1424.2–1446.0 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1432.4 1428.0–1436.8 | 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 | 1429.7 1422.6–1436.8 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1428.7 1423.9–1433.4 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1427.0 1414.1–1440.0 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1424.0 1413.6–1434.3 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1422.5 1412.1–1433.0 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1420.4 1413.4–1427.4 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1418.1 1401.2–1435.0 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1418.0 1405.0–1431.0 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1417.7 1399.9–1435.5 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1417.0 1411.3–1422.7 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1416.1 1412.6–1419.6 | 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 | 1412.9 1406.1–1419.8 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1407.7 1399.1–1416.3 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1403.9 1398.2–1409.6 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1403.6 1398.7–1408.5 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1402.0 1391.1–1413.0 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1401.0 1378.6–1423.4 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1399.2 1394.7–1403.7 | 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 | 1393.7 1387.4–1399.9 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1376.1 1368.6–1383.5 | 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 | 1373.1 1366.4–1379.9 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1349.0 1325.7–1372.4 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 68.0 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 4.1 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 80.7 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | 34.7 % | independent | Artificial Analysis | |
| IFBench | 36.2 % | independent | Artificial Analysis |
reasoning math
| AIME year=2025 · implementation=artificial-analysis | 38.0 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Mistral Large 3 | Terminal-Bench Hard | 15.9 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Mistral Large 3 | Terminal-Bench 2.1 | 12.0 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.