Other · model
Magistral Medium benchmark scores
As of 2026-10-29, Magistral Medium (Other) has measured scores on 13 benchmarks and estimated scores on 38 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 67.9% | measured |
| AA-HLE | 9.8% | measured |
| AA-SciCode | 16.5% | estimated ± 4.7 pp, medium confidence |
| AIME26 | 66.7% | estimated ± 4.6 pp, medium confidence |
| CritPt | 0.3% | measured |
| GDPval-AA | 0.0% | estimated ± 10.9 pp, low confidence |
| GPQA Diamond | 71.0% | estimated ± 1.2 pp, high confidence |
| HLE | 9.4% | estimated ± 6.9 pp, medium confidence |
| IFBench | 53.6% | estimated ± 6.6 pp, low confidence |
| AA-LCR | 0.0% | measured |
| LiveCodeBench v6 | 50.3% | measured |
| SciCode | 16.9% | estimated ± 4.9 pp, medium confidence |
| IFEval | 78.6% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 47.1% | estimated ± 5.8 pp, low confidence |
| τ²-bench results | 23.1% | measured |
| AA Coding Index | 6.1% | estimated ± 5.6 pp, medium confidence |
| BioMysteryBench (human-difficult) | 6.5% | estimated ± 6.8 pp, low confidence |
| SWE-bench Verified | 57.5% | estimated ± 9.2 pp, low confidence |
| BFCL v4 | 22.7% | estimated ± 8.5 pp, low confidence |
| SWE-bench Pro | 0.0% | estimated ± 6.0 pp, low confidence |
| AA Agentic Index | 0.0% | estimated ± 12.3 pp, low confidence |
| MMLU-Pro | 73.2% | estimated ± 4.1 pp, high confidence |
| AA-IFBench | 25.1% | measured |
| AIME 2024 | 73.6% | measured |
| Artificial Analysis Intelligence Index | 9.0% | measured |
| GPQA | 70.8% | measured |
| MMLU | 85.7% | estimated ± 0.7 pp, high confidence |
| AA-Omniscience Accuracy | 20.3% | measured |
| MATH-500 | 94.3% | measured |
| MMMLU | 85.4% | estimated ± 0.7 pp, medium confidence |
| AA MMLU-Pro | 83.5% | estimated ± 0.6 pp, medium confidence |
| AIME 2025 | 64.9% | measured |
| ARC-AGI-1 | 16.9% | estimated ± 7.0 pp, low confidence |
| ARC-AGI-2 | 0.0% | estimated ± 11.6 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 |
| HLE w/o tools | 28.9% | estimated ± 4.6 pp, medium confidence |
| ARC-AGI-3 | 1.4% | estimated ± 7.7 pp, low confidence |
| C-Eval | 88.3% | estimated ± 1.0 pp, low confidence |
| HMMT Feb 2025 | 34.3% | estimated ± 3.1 pp, medium confidence |
| MMLU-Redux | 93.5% | estimated ± 0.8 pp, medium confidence |
| SuperGPQA | 50.8% | estimated ± 8.2 pp, low confidence |
| HealthBench Hard | 3.5% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 78.3% | estimated ± 4.0 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.3 pp, medium confidence |
| HealthBench Professional (raw) | 50.1% | estimated ± 8.6 pp, low confidence |
| HLE-Verified | 15.7% | estimated ± 7.1 pp, low confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 18.5% | estimated ± 4.3 pp, medium confidence |
| MRCRv2 | 22.8% | estimated ± 11.3 pp, low confidence |