Mistral · model
Mistral Large 3 benchmark scores
As of 2026-11-22, Mistral Large 3 (Mistral) has measured scores on 18 benchmarks and estimated scores on 96 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 68.0% | measured |
| AA-HLE | 4.2% | measured |
| AA-SciCode | 36.6% | measured |
| Artificial Analysis Intelligence Index | 9.3% | measured |
| CritPt | 0.0% | measured |
| GDPval-AA | 0.0% | measured |
| GPQA Diamond | 84.0% | estimated ± 1.9 pp, medium confidence |
| HLE | 16.7% | estimated ± 8.5 pp, low confidence |
| IFBench | 53.9% | estimated ± 6.6 pp, low confidence |
| AA-LCR | 36.0% | measured |
| LiveCodeBench v6 | 71.3% | estimated ± 4.7 pp, high confidence |
| AA-Omniscience Accuracy | 25.0% | measured |
| SciCode | 36.8% | estimated ± 3.1 pp, high confidence |
| BrowseComp | 20.7% | estimated ± 9.0 pp, low confidence |
| HLE w/ tools | 33.8% | estimated ± 5.3 pp, low confidence |
| IFEval | 87.4% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 51.3% | estimated ± 5.5 pp, medium confidence |
| τ²-bench results | 24.6% | measured |
| AA Coding Index | 20.1% | measured |
| AA-MMMU-Pro | 55.7% | measured |
| APEX-Agents | 0.0% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 6.0% | estimated ± 9.5 pp, medium confidence |
| BioMysteryBench (human-difficult) | 0.0% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 38.9% | estimated ± 4.5 pp, medium confidence |
| SWE-bench Verified | 62.0% | estimated ± 4.4 pp, medium confidence |
| BFCL v4 | 53.9% | estimated ± 2.7 pp, high confidence |
| CyberGym | 47.4% | estimated ± 5.3 pp, low confidence |
| JobBench | 0.0% | estimated ± 8.7 pp, low confidence |
| SWE-bench Pro | 57.2% | estimated ± 4.7 pp, medium confidence |
| WideResearch | 0.0% | estimated ± 7.8 pp, low confidence |
| AA Agentic Index | 2.4% | measured |
| MMLU-Pro | 81.8% | estimated ± 4.8 pp, high confidence |
| AA-IFBench | 36.2% | measured |
| FailureSensorIQ | 62.0% | estimated ± 1.7 pp, medium confidence |
| GPQA | 71.6% | estimated ± 4.5 pp, high confidence |
| MMLU | 90.5% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 68.4% | measured |
| Vals LiveCodeBench | 55.3% | measured |
| Vals MMLU-Pro | 79.8% | measured |
| MMMLU | 83.3% | estimated ± 0.7 pp, medium confidence |
| MMMU | 69.7% | estimated ± 2.7 pp, high confidence |
| Chess Puzzles | 19.3% | estimated ± 12.3 pp, low confidence |
| AA MMLU-Pro | 84.8% | estimated ± 0.8 pp, high confidence |
| Gert Labs | 26.9% | estimated ± 10.0 pp, low confidence |
| AA Harvey LAB v1.0 | 79.4% | estimated ± 1.2 pp, low confidence |
| AA Tau3 Banking | 17.4% | estimated ± 3.7 pp, medium confidence |
| ARC-AGI-1 | 40.3% | estimated ± 6.5 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 13.8 pp, low confidence |
| CursorBench 3.2 | 32.3% | estimated ± 5.3 pp, low confidence |
| FrontierSWE v2 | 3.3% | estimated ± 14.2 pp, low confidence |
| MazeBench | 0.4% | estimated ± 5.5 pp, low confidence |
| Mystery Game Puzzles | 13.5% | estimated ± 14.6 pp, low confidence |
| NYT Connections | 7.5% | measured |
| OSWorld-Verified | 55.4% | estimated ± 8.4 pp, low confidence |
| ParseBench-1 | 44.2% | estimated ± 6.2 pp, medium confidence |
| Vals SWE-bench | 41.4% | measured |
| VulcanBench v3 | 76.5% | estimated ± 5.6 pp, low confidence |
| CWE-Bench-AA | 0.0% | estimated ± 10.1 pp, low confidence |
| AA Cyber Index | 1.8% | estimated ± 9.2 pp, low confidence |
| DeepsecBench-AA | 0.0% | estimated ± 8.9 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 48.6% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 40.1% | estimated ± 1.1 pp, low confidence |
| AA ITBench | 33.6% | estimated ± 4.0 pp, medium confidence |
| Bug Hunt Bench | 12.6% | estimated ± 10.5 pp, low confidence |
| CursorBench 4.0 | 23.6% | estimated ± 4.9 pp, medium confidence |
| CWE-bench v1 | 0.0% | estimated ± 6.4 pp, low confidence |
| DeepSWE | 22.3% | estimated ± 7.5 pp, low confidence |
| DRACO | 0.0% | estimated ± 2.0 pp, low confidence |
| FrontierCode 2.0 | 26.1% | estimated ± 9.3 pp, low confidence |
| HLE w/o tools | 24.7% | estimated ± 4.9 pp, high confidence |
| PostTrainBench v1.1 | 25.0% | estimated ± 7.4 pp, low confidence |
| StealthMark | 41.3% | estimated ± 10.7 pp, low confidence |
| Toolathlon-Verified | 9.2% | estimated ± 2.3 pp, low confidence |
| VulcanBench Frontier v4 | 65.8% | estimated ± 6.8 pp, low confidence |
| GDP.pdf | 17.0% | estimated ± 4.6 pp, medium confidence |
| ARC-AGI-3 | 1.3% | estimated ± 9.8 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| SkillsBench official leaderboard (BenchFlow) | 18.0% | estimated ± 6.1 pp, low confidence |
| BinaryAudit | 9.9% | estimated ± 12.1 pp, low confidence |
| OTelBench | 6.8% | estimated ± 6.6 pp, low confidence |
| Vibe Code Bench | 5.4% | estimated ± 10.0 pp, low confidence |
| Hermes Bench | 0.0% | estimated ± 2.9 pp, medium confidence |
| Hermes Index | 0.0% | estimated ± 8.7 pp, low confidence |
| ParseBench-2 | 41.5% | estimated ± 6.2 pp, medium confidence |
| CharXiv | 67.1% | estimated ± 6.3 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 12.2 pp, low confidence |
| AI2D_TEST | 88.0% | estimated ± 2.0 pp, medium confidence |
| C-Eval | 88.4% | estimated ± 1.0 pp, low confidence |
| MCP Atlas | 64.6% | estimated ± 7.8 pp, low confidence |
| MMLU-Redux | 94.1% | estimated ± 0.8 pp, medium confidence |
| MMMU-Pro | 56.5% | estimated ± 1.5 pp, high confidence |
| NL2Repo | 35.4% | estimated ± 4.7 pp, medium confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| ScreenSpot Pro | 61.2% | estimated ± 10.8 pp, low confidence |
| SuperGPQA | 65.8% | estimated ± 9.3 pp, medium confidence |
| Toolathlon | 27.0% | estimated ± 6.3 pp, low confidence |
| Video-MME (w/o subtitle) | 73.0% | estimated ± 1.7 pp, medium confidence |
| AA LiveCodeBench | 81.4% | estimated ± 2.6 pp, high confidence |
| HealthBench Hard | 0.0% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 77.1% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 69.1% | estimated ± 3.2 pp, medium confidence |
| ResearchClawBench | 4.5% | estimated ± 1.9 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (length-adjusted) | 54.1% | estimated ± 3.7 pp, medium confidence |
| HealthBench Professional | 56.7% | estimated ± 4.2 pp, low confidence |
| HLE-Verified | 19.8% | estimated ± 7.1 pp, low confidence |
| ScarfBench | 24.4% | estimated ± 9.1 pp, low confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 25.0% | estimated ± 4.3 pp, medium confidence |
| OpenHarmony Bench v1.0 | 51.0% | estimated ± 2.4 pp, medium confidence |
| MRCRv2 | 22.8% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 57.5% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 34.1% | estimated ± 3.8 pp, low confidence |
| MMMU-Pro w/ Python | 60.9% | estimated ± 2.0 pp, medium confidence |