Mistral Large 4.
Mistral AI Oct 2026 Flagship
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BullshitBench V2 | 80% | #11 of 122 | Official leaderboard | |
| LMArena (Elo) | 1,432 | #89 of 333 | Official leaderboard | |
| Extended NYT Connections | 27.4% | #78 of 97 | Official leaderboard | |
| SimpleQA Verified | 20% | #72 of 84 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | #28 of 202 | Epoch AI | |
| GPQA Diamond | 88.1% | #55 of 219 | Epoch AI | |
| DTBench | 80.4% | #56 of 178 | Official leaderboard | |
| CritPt | 10.6% | #57 of 160 | Epoch AI | |
| FrontierMath Tiers 1-3 v2 | 58.6% | #44 of 89 | Epoch AI | |
| FrontierMath Tier 4 v2 | 26.8% | #43 of 71 | Epoch AI | |
| LatchBio Capabilities v1.0 | 34.9% | #22 of 27 | Official leaderboard | |
| ProofBench | 10% | #68 of 83 | Epoch AI | |
| Surface Evolver Bench | 28.1% | #22 of 26 | Epoch AI | |
| ProofBench v1.1 | 10% | #46 of 51 | Official leaderboard | |
| FrontierPhysics | 0.60% | #18 of 19 | Official leaderboard | |
| MysteryMechanism | 12.2% | #29 of 29 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vibe Code Bench | 78.4% | #32 of 115 | Official leaderboard | |
| ALE-Bench | 1,213 | #39 of 121 | Epoch AI | |
| Code Arena | 1,544 | #42 of 124 | Official leaderboard | |
| Code Migration | 30.6% | #42 of 78 | Official leaderboard | |
| FrontierCode | 39.4% | #28 of 46 | Epoch AI | |
| DeepSWE | 61.7% | #33 of 51 | Model card | |
| FrontierCode 2.0 | 19.6% | #17 of 26 | Official leaderboard | |
| IOI v2 (Vals) | 45.3% | #32 of 45 | Official leaderboard | |
| Vibe Code Bench 1-100 | 14.3% | #21 of 26 | Official leaderboard | |
| WeirdML v3 | 4.45% | #24 of 25 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AutomationBench | 59.9% | #4 of 41 | Model card | |
| Chess Puzzles | 33% | #47 of 83 | Epoch AI | |
| Mystery Game Puzzles | 17% | #59 of 80 | Epoch AI | |
| Agent Arena | -0.06 | #40 of 53 | Official leaderboard | |
| Terminal-Bench 4.0 | 28.3% | #20 of 23 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Harvey LAB (Legal Agent Benchmark) | 15.8% | #10 of 80 | Official leaderboard | |
| Harvey LAB v1.1 (HLAB-Vals-1.1) | 17.5% | #6 of 33 | Official leaderboard | |
| Legora BAR | 103.0 | #5 of 17 | Official leaderboard | |
| Vals Finance Agent v2 | 54.7% | #26 of 80 | Official leaderboard | |
| Tax Agent Bench | 30.4% | #29 of 79 | Official leaderboard | |
| APEX-Agents | 51.6% | #28 of 56 | Epoch AI | |
| Vals Finance Agent v2.1 | 61.4% | #18 of 35 | Official leaderboard | |
| Excel Modeling Benchmark v1.1 | 69% | #20 of 37 | Official leaderboard | |
| MedScribe | 80.4% | #53 of 98 | Official leaderboard | |
| Vals Finance Index | 56.9% | #19 of 35 | Official leaderboard | |
| Legal Research Bench | 31.7% | #48 of 88 | Official leaderboard | |
| MedCode | 40.7% | #58 of 96 | Official leaderboard | |
| Excel Modeling Benchmark | 56.2% | #47 of 76 | Official leaderboard | |
| Immigration Bench | 63.7% | #18 of 24 | Official leaderboard | |
| Vals Legal Index | 65.6% | #26 of 33 | Official leaderboard | |
| TaxCalcBench v2 | 4.00% | #23 of 26 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vision Arena | 1,252 | #43 of 136 | Official leaderboard | |
| Furniture Assembly Benchmark | 20.8% | #34 of 35 | Epoch AI | |
| Dense 200 (bbox) | 42% | #2 of 2 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| DistressBench | 77% | #9 of 42 | Official leaderboard | |
| KORA | 60.7% | #10 of 42 | Official leaderboard | |
| OncologyBench | 22.7% | #9 of 30 | Official leaderboard | |
| FORTRESS | 23.1% | #31 of 66 | Official leaderboard | |
| EpiBench | 20.8% | #20 of 27 | Official leaderboard | |
| BioSecBench-Function | 28.8% | #21 of 27 | Official leaderboard | |
| TxBench-Preclinical-Pharmacology | 42.3% | #22 of 28 | Official leaderboard | |
| VariantBench | 28% | #22 of 27 | Official leaderboard | |
| TxBench-Antibody-Discovery | 28.3% | #23 of 28 | Official leaderboard | |
| MetagenomicsBench | 26.3% | #23 of 26 | Official leaderboard | |
| SpatialBench-Long | 20.8% | #24 of 27 | Official leaderboard | |
| TxBench-Oligo-Discovery | 27.1% | #25 of 28 | Official leaderboard | |
| BioSecBench-Refusal | 3.40% | #20 of 22 | Official leaderboard | |
| BioSecBench-Surveillance | 34% | #25 of 27 | Official leaderboard | |
| scBench-Long | 10.2% | #25 of 27 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Conceptual Reasoning Index | 50.7 | #65 of 149 | Official leaderboard | |
| ACCoRD | 65.7 | #69 of 150 | Official leaderboard | |
| LMCA | 35.8% | #69 of 139 | Epoch AI | |
| LiveBench | 43.9% | #27 of 28 | Official leaderboard |
Mistral AI's models in color, against every other model on the Epoch Capabilities Index, by release date.
The benchmarks the lab chose to headline, with the scores it gave.