Mistral · model
Mistral Small 3.1 benchmark scores
As of 2026-10-29, Mistral Small 3.1 (Mistral) has measured scores on 16 benchmarks and estimated scores on 84 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 45.4% | measured |
| AA-HLE | 4.3% | measured |
| AA-SciCode | 27.8% | measured |
| CritPt | 0.0% | measured |
| GDPval-AA | 0.0% | measured |
| GPQA Diamond | 46.4% | estimated ± 1.2 pp, high confidence |
| HLE | 1.3% | estimated ± 6.9 pp, low confidence |
| IFBench | 53.7% | estimated ± 6.6 pp, low confidence |
| AA-LCR | 22.3% | measured |
| LiveCodeBench v6 | 68.6% | estimated ± 4.9 pp, high confidence |
| SciCode | 28.3% | estimated ± 3.1 pp, high confidence |
| BrowseComp | 0.0% | estimated ± 9.0 pp, low confidence |
| HLE w/ tools | 33.8% | estimated ± 5.3 pp, low confidence |
| IFEval | 83.6% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 51.3% | estimated ± 5.8 pp, low confidence |
| τ²-bench results | 25.1% | measured |
| AA Coding Index | 15.2% | estimated ± 6.1 pp, medium confidence |
| AA-MMMU-Pro | 48.9% | estimated ± 1.6 pp, high confidence |
| APEX-Agents | 0.0% | estimated ± 9.0 pp, low confidence |
| APEX-Agents-AA | 5.4% | estimated ± 9.4 pp, medium confidence |
| BioMysteryBench (human-difficult) | 0.0% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 34.7% | estimated ± 9.6 pp, medium confidence |
| SWE-bench Verified | 48.3% | estimated ± 6.4 pp, medium confidence |
| BFCL v4 | 53.9% | estimated ± 2.7 pp, high confidence |
| CyberGym | 0.0% | estimated ± 6.0 pp, low confidence |
| JobBench | 0.0% | estimated ± 8.7 pp, low confidence |
| SWE-bench Pro | 24.8% | estimated ± 6.6 pp, medium confidence |
| WideResearch | 0.0% | estimated ± 7.8 pp, low confidence |
| AA Agentic Index | 0.0% | estimated ± 2.9 pp, high confidence |
| MMLU-Pro | 66.8% | measured |
| AA-IFBench | 29.9% | measured |
| Artificial Analysis Intelligence Index | 7.1% | measured |
| BBH | 84.8% | estimated ± 2.4 pp, low confidence |
| GPQA | 46.0% | measured |
| MMLU | 80.6% | measured |
| AA-Omniscience Accuracy | 15.1% | measured |
| MMMLU | 83.3% | estimated ± 0.7 pp, medium confidence |
| MMMU | 64.0% | measured |
| AA MMLU-Pro | 82.7% | estimated ± 0.6 pp, medium confidence |
| Gert Labs | 31.4% | estimated ± 8.9 pp, medium confidence |
| AA Tau3 Banking | 0.0% | estimated ± 4.0 pp, medium confidence |
| ARC-AGI-1 | 49.4% | estimated ± 7.6 pp, low confidence |
| ARC-AGI-2 | 30.7% | estimated ± 14.6 pp, low confidence |
| FrontierSWE v2 | 0.6% | estimated ± 14.6 pp, low confidence |
| MazeBench | 0.4% | estimated ± 5.4 pp, low confidence |
| OSWorld-Verified | 62.6% | estimated ± 8.1 pp, low confidence |
| ParseBench | 35.2% | estimated ± 6.2 pp, low confidence |
| Vals GPQA Diamond | 81.3% | estimated ± 5.3 pp, low confidence |
| Vals MMLU-Pro | 83.9% | estimated ± 2.1 pp, medium confidence |
| Vals SWE-bench | 51.0% | estimated ± 7.5 pp, low confidence |
| AA AutomationBench | 0.0% | estimated ± 14.8 pp, low confidence |
| CWE-Bench-AA | 0.0% | estimated ± 9.8 pp, low confidence |
| DeepsecBench-AA | 0.0% | estimated ± 8.6 pp, low confidence |
| GDP.pdf | 0.0% | estimated ± 5.2 pp, low confidence |
| AA ITBench | 35.7% | estimated ± 5.1 pp, low confidence |
| CWE-bench v1 | 0.0% | estimated ± 6.4 pp, low confidence |
| DeepSWE | 5.2% | estimated ± 7.5 pp, low confidence |
| HLE w/o tools | 28.6% | estimated ± 4.6 pp, medium confidence |
| Toolathlon-Verified | 0.0% | estimated ± 3.1 pp, medium confidence |
| ARC-AGI-3 | 1.4% | estimated ± 7.7 pp, low confidence |
| Hermes Bench | 0.0% | estimated ± 2.9 pp, medium confidence |
| Hermes Index | 0.0% | estimated ± 8.7 pp, low confidence |
| CharXiv | 40.9% | estimated ± 5.2 pp, low confidence |
| CharXiv w/o tools | 70.4% | estimated ± 2.5 pp, medium confidence |
| AI2D_TEST | 87.8% | estimated ± 2.0 pp, high confidence |
| C-Eval | 87.7% | estimated ± 1.0 pp, low confidence |
| CountBench | 92.2% | estimated ± 3.0 pp, high confidence |
| DynaMath | 79.1% | estimated ± 5.3 pp, low confidence |
| ERQA | 47.1% | estimated ± 5.2 pp, low confidence |
| MathVision | 55.0% | estimated ± 2.9 pp, high confidence |
| MCP Atlas | 56.5% | estimated ± 10.7 pp, low confidence |
| MLVU (M-Avg) | 73.0% | estimated ± 2.2 pp, high confidence |
| MMLU-Redux | 82.0% | estimated ± 0.6 pp, high confidence |
| MMMU-Pro | 49.3% | measured |
| NL2Repo | 10.7% | estimated ± 7.4 pp, low confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| RealWorldQA | 79.4% | estimated ± 2.9 pp, high confidence |
| ScreenSpot Pro | 53.0% | estimated ± 7.3 pp, low confidence |
| SimpleVQA | 47.2% | estimated ± 7.1 pp, medium confidence |
| SuperGPQA | 64.4% | estimated ± 9.3 pp, low confidence |
| Toolathlon | 27.0% | estimated ± 6.3 pp, low confidence |
| Video-MME (w/o subtitle) | 67.4% | estimated ± 1.3 pp, high confidence |
| Video-MME (with subtitle) | 70.4% | estimated ± 3.0 pp, high confidence |
| VideoMMMU | 55.0% | estimated ± 3.8 pp, high confidence |
| We-Math | 71.8% | estimated ± 7.2 pp, low 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 | 67.2% | estimated ± 4.7 pp, low confidence |
| ResearchClawBench | 0.0% | estimated ± 2.2 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| DRACO | 61.5% | estimated ± 3.1 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.3 pp, medium confidence |
| HealthBench Professional (raw) | 49.2% | estimated ± 8.6 pp, low confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 10.4% | measured |
| MMVU | 56.8% | estimated ± 2.7 pp, medium confidence |
| MRCRv2 | 22.8% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 53.7% | estimated ± 2.6 pp, low confidence |
| MMMU-Pro w/ Python | 59.8% | estimated ± 2.6 pp, medium confidence |
| OCRBench V2 | 61.9% | estimated ± 4.4 pp, medium confidence |