DeepSeek · model
DeepSeek V3.1 (Reasoning) benchmark scores
As of 2026-10-07, DeepSeek V3.1 (Reasoning) (DeepSeek) has measured scores on 8 benchmarks and estimated scores on 34 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 77.9% | measured |
| AA-HLE | 14.3% | measured |
| Artificial Analysis Intelligence Index | 13.5% | measured |
| CritPt | 2.0% | measured |
| GDPval-AA | 0.2% | estimated ± 12.5 pp, low confidence |
| GPQA Diamond | 77.4% | estimated ± 2.2 pp, high confidence |
| HLE | 30.9% | estimated ± 9.5 pp, medium confidence |
| IFBench | 56.0% | estimated ± 6.9 pp, low confidence |
| AA-LCR | 56.7% | measured |
| AA-Omniscience Accuracy | 29.0% | measured |
| IFEval | 89.1% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 1.5% | estimated ± 5.9 pp, low confidence |
| τ²-bench results | 37.4% | measured |
| APEX-Agents-AA | 1.6% | estimated ± 11.4 pp, low confidence |
| BioMysteryBench (human-difficult) | 34.3% | estimated ± 5.9 pp, low confidence |
| BFCL v4 | 45.1% | estimated ± 9.8 pp, low confidence |
| AA Agentic Index | 3.3% | estimated ± 12.3 pp, low confidence |
| MMLU-Pro | 85.7% | estimated ± 3.5 pp, high confidence |
| GPQA | 75.1% | estimated ± 3.2 pp, high confidence |
| AA-IFBench | 41.5% | measured |
| AA EnterpriseOps-Gym | 1.4% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-1 | 11.1% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-2 | 3.4% | estimated ± 14.2 pp, low confidence |
| Vals GPQA Diamond | 69.2% | estimated ± 7.4 pp, medium confidence |
| Vals MMLU-Pro | 84.8% | estimated ± 2.2 pp, high confidence |
| AA ITBench | 98.8% | estimated ± 3.6 pp, low confidence |
| HLE w/o tools | 11.8% | estimated ± 5.7 pp, medium confidence |
| C-Eval | 87.3% | estimated ± 1.0 pp, low confidence |
| MCP-Tasks | 100.0% | estimated ± 8.2 pp, low confidence |
| MMLU-Redux | 95.3% | estimated ± 1.1 pp, medium confidence |
| SuperGPQA | 73.7% | estimated ± 7.5 pp, medium confidence |
| HealthBench Hard | 0.9% | estimated ± 7.7 pp, low confidence |
| MMLU-Pro (Arcee) | 84.6% | estimated ± 4.0 pp, medium 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) | 20.8% | 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) | 33.6% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 60.1% | estimated ± 1.8 pp, low confidence |
| MMLU | 90.5% | estimated ± 1.1 pp, medium confidence |