Mistral · model
Mistral Medium 3 benchmark scores
As of 2026-10-07, Mistral Medium 3 (Mistral) has measured scores on 9 benchmarks and estimated scores on 46 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 57.8% | measured |
| AA-HLE | 4.1% | measured |
| Artificial Analysis Intelligence Index | 9.0% | measured |
| CritPt | 0.0% | measured |
| GDPval-AA | 0.0% | estimated ± 12.5 pp, low confidence |
| GPQA Diamond | 68.8% | estimated ± 2.2 pp, medium confidence |
| HLE | 19.0% | estimated ± 9.5 pp, medium confidence |
| IFBench | 55.8% | estimated ± 6.9 pp, low confidence |
| AA-LCR | 31.3% | measured |
| AA-Omniscience Accuracy | 18.3% | measured |
| IFEval | 88.2% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 0.0% | estimated ± 5.9 pp, low confidence |
| τ²-bench results | 24.3% | measured |
| AA-MMMU-Pro | 53.0% | measured |
| APEX-Agents-AA | 1.6% | estimated ± 11.4 pp, low confidence |
| BioMysteryBench (human-difficult) | 25.5% | estimated ± 5.9 pp, low confidence |
| BFCL v4 | 44.9% | estimated ± 9.8 pp, low confidence |
| AA Agentic Index | 0.0% | estimated ± 12.3 pp, low confidence |
| MMLU-Pro | 84.5% | estimated ± 3.5 pp, high confidence |
| GPQA | 57.8% | estimated ± 3.2 pp, high confidence |
| AA-IFBench | 39.3% | measured |
| AA EnterpriseOps-Gym | 1.2% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-1 | 1.5% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-2 | 0.6% | estimated ± 14.2 pp, low confidence |
| OfficeQA Pro | 50.3% | estimated ± 7.2 pp, low confidence |
| Vals GPQA Diamond | 44.1% | estimated ± 7.4 pp, low confidence |
| Vals MMLU-Pro | 82.8% | estimated ± 2.2 pp, high confidence |
| AA ITBench | 99.9% | estimated ± 3.6 pp, low confidence |
| HLE w/o tools | 3.2% | estimated ± 5.7 pp, low confidence |
| CharXiv | 70.3% | estimated ± 7.5 pp, low confidence |
| CharXiv w/o tools | 63.7% | estimated ± 2.4 pp, medium confidence |
| C-Eval | 82.0% | estimated ± 1.0 pp, low confidence |
| MathVision | 81.5% | estimated ± 4.9 pp, high confidence |
| MCP-Tasks | 100.0% | estimated ± 8.2 pp, low confidence |
| MMLU-Redux | 92.6% | estimated ± 1.1 pp, medium confidence |
| MMMU-Pro | 66.2% | estimated ± 4.4 pp, medium confidence |
| ScreenSpot Pro | 58.6% | estimated ± 10.7 pp, low confidence |
| SuperGPQA | 61.8% | estimated ± 7.5 pp, medium confidence |
| ERQA | 0.0% | estimated ± 3.9 pp, medium confidence |
| HealthBench Hard | 0.1% | estimated ± 7.7 pp, low confidence |
| MedXpertQA (MM) | 0.2% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 77.1% | estimated ± 4.0 pp, low confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 6.5% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 57.7% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 20.8% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 38.3% | estimated ± 1.8 pp, low confidence |
| MMMU | 70.8% | estimated ± 0.9 pp, medium confidence |
| MMLU | 85.0% | estimated ± 1.1 pp, medium confidence |
| MMMU-Pro w/ Python | 62.8% | estimated ± 1.6 pp, medium confidence |
| RealWorldQA | 70.7% | estimated ± 1.2 pp, low confidence |
| OmniDocBench 1.5 | 0.0% | estimated ± 6.4 pp, low confidence |