Mistral Medium 3.5
Mistral Medium 3.5.
46
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Mistral AI Apr 2026 Mistral Medium 3.5
Open weights Mid-size
141.5
#117 of 271
Epoch Capabilities Index
- IFBench 69% #44 /70
- Harvey LAB (Legal Agent Benchmark) 0.42% #61 /80
- CritPt 0% #156 /160
Where it ranks
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.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMArena (Elo) | 1,426 | #95 of 333 | Official leaderboard | |
| COLLIE | 95.8% | #4 of 12 | Model card | |
| Phare | 64.3% | #36 of 62 | Official leaderboard | |
| IFBench | 69% | #44 of 70 | Model card | |
| SEA-HELM | 64.7 | #41 of 62 | Official leaderboard | |
| Extended NYT Connections | 12.9% | #89 of 97 | Official leaderboard | |
| EQ-Bench 4 | 983 | #32 of 32 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIME 2025 | 86.3% | #68 of 143 | Model card | |
| Beyond AIME | 66.9% | #7 of 14 | Model card | |
| DTBench | 59.1% | #103 of 178 | Official leaderboard | |
| ProofBench | 10% | #44 of 59 | Official leaderboard | |
| Surface Evolver Bench | 26.9% | #23 of 26 | Epoch AI | |
| ProofBench v1.1 | 9.00% | #47 of 51 | Official leaderboard | |
| CritPt | 0% | #156 of 160 | Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SWE-bench Verified | 77.6% | #31 of 150 | Model card | |
| WeirdML | 43.7% | #65 of 130 | Epoch AI | |
| ALE-Bench | 764 | #77 of 121 | Epoch AI | |
| Code Arena | 1,264 | #109 of 124 | Official leaderboard | |
| WebDev Arena | 1,265 | #93 of 105 | Epoch AI | |
| Code Migration | 5.13% | #71 of 78 | Official leaderboard | |
| Vibe Code Bench | 2.89% | #109 of 115 | Official leaderboard | |
| FrontierCode | 8.00% | #46 of 46 | Epoch AI |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PACT | 1,538 | #11 of 26 | Official leaderboard | |
| tau3-bench | 63.2% | #9 of 12 | Model card | |
| BrowseComp | 48.6% | #61 of 77 | Model card | |
| Agent Arena | -0.13 | #48 of 53 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CorpFin v2 | 58.8% | #78 of 119 | Official leaderboard | |
| Vals Finance Agent | 46.1% | #34 of 49 | Official leaderboard | |
| TaxEval v2 | 68% | #95 of 129 | Official leaderboard | |
| Harvey LAB (Legal Agent Benchmark) | 0.42% | #61 of 80 | Official leaderboard | |
| MedCode | 33.8% | #78 of 96 | Official leaderboard | |
| Vals Finance Agent v2 | 32.1% | #70 of 80 | Official leaderboard | |
| MedScribe | 67.7% | #89 of 98 | Official leaderboard | |
| Legal Research Bench | 9.13% | #81 of 88 | Official leaderboard | |
| Tax Agent Bench | 4.48% | #76 of 79 | Official leaderboard | |
| Excel Modeling Benchmark | 11.2% | #74 of 76 | Official leaderboard | |
| MortgageTax | 28.9% | #84 of 86 | Official leaderboard | |
| CaseLaw v2 | 44.2% | #52 of 53 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vision Arena | 1,200 | #79 of 136 | Official leaderboard | |
| GeoBench | 56% | #38 of 48 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMCA | 26.1% | #93 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 36.6 | #104 of 149 | Official leaderboard | |
| SAGE (Vals) | 37.6% | #62 of 81 | Official leaderboard | |
| ACCoRD | 45.6 | #117 of 150 | Official leaderboard | |
| SAGE v1.1 (Vals) | 72% | #27 of 28 | Official leaderboard | |
| Vals Multimodal Index | 34.8% | #33 of 33 | Official leaderboard |
Mistral AI's models over time
Mistral AI's models in color, against every other model on the Epoch Capabilities Index, by release date.
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.