xAI · model
Grok 4.1 Fast (Reasoning) benchmark scores
As of 2026-10-07, Grok 4.1 Fast (Reasoning) (xAI) has measured scores on 10 benchmarks and estimated scores on 54 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 85.3% | measured |
| AA-HLE | 19.3% | measured |
| AA-SciCode | 45.9% | estimated ± 3.8 pp, high confidence |
| Artificial Analysis Intelligence Index | 20.4% | measured |
| CritPt | 2.9% | measured |
| GDPval-AA | 26.8% | estimated ± 12.5 pp, low confidence |
| GPQA Diamond | 80.9% | estimated ± 2.2 pp, high confidence |
| HLE | 33.2% | estimated ± 9.5 pp, medium confidence |
| IFBench | 58.2% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 74.0% | measured |
| AA-Omniscience Accuracy | 25.1% | measured |
| IFEval | 91.8% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| τ²-bench results | 93.3% | measured |
| AA Coding Index | 39.3% | estimated ± 6.8 pp, medium confidence |
| AA-MMMU-Pro | 63.3% | measured |
| APEX-Agents-AA | 25.3% | estimated ± 11.4 pp, low confidence |
| BioMysteryBench (human-difficult) | 31.4% | estimated ± 5.9 pp, low confidence |
| SWE-bench Verified | 71.9% | estimated ± 4.4 pp, high confidence |
| BFCL v4 | 68.8% | estimated ± 9.8 pp, low confidence |
| AA Agentic Index | 23.9% | estimated ± 12.3 pp, low confidence |
| MMLU-Pro | 85.6% | estimated ± 3.5 pp, high confidence |
| GPQA | 85.6% | estimated ± 3.2 pp, high confidence |
| AA-IFBench | 52.7% | measured |
| AA EnterpriseOps-Gym | 43.6% | estimated ± 3.6 pp, medium confidence |
| ARC-AGI-1 | 51.9% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-2 | 17.8% | estimated ± 14.2 pp, low confidence |
| FrontierCode 1.1 Main | 0.4% | estimated ± 4.3 pp, low confidence |
| OfficeQA Pro | 50.3% | estimated ± 7.2 pp, low confidence |
| Vals GPQA Diamond | 80.6% | estimated ± 7.4 pp, medium confidence |
| Vals MMLU-Pro | 84.1% | estimated ± 2.2 pp, high confidence |
| Vals SWE-bench | 62.6% | estimated ± 6.3 pp, medium confidence |
| AA ITBench | 46.6% | estimated ± 3.6 pp, medium confidence |
| HLE w/o tools | 16.4% | estimated ± 5.7 pp, medium confidence |
| PostTrainBench v1.1 | 19.9% | estimated ± 10.5 pp, low confidence |
| Vibe Code Bench | 1.2% | measured |
| CharXiv | 70.4% | estimated ± 7.5 pp, low confidence |
| CharXiv w/o tools | 71.6% | estimated ± 2.4 pp, medium confidence |
| C-Eval | 91.3% | estimated ± 1.0 pp, medium confidence |
| MathVision | 81.5% | estimated ± 4.9 pp, high confidence |
| MCP-Tasks | 67.4% | estimated ± 8.2 pp, low confidence |
| MMLU-Redux | 94.6% | estimated ± 1.1 pp, medium confidence |
| MMMU-Pro | 71.4% | estimated ± 4.4 pp, medium confidence |
| ScreenSpot Pro | 63.6% | estimated ± 10.7 pp, low confidence |
| SuperGPQA | 70.1% | estimated ± 7.5 pp, medium confidence |
| ERQA | 1.9% | estimated ± 3.9 pp, medium confidence |
| HealthBench Hard | 8.2% | estimated ± 7.7 pp, low confidence |
| MedXpertQA (MM) | 10.3% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 88.0% | estimated ± 4.0 pp, medium confidence |
| React Native Evals | 13.2% | estimated ± 3.0 pp, low confidence |
| SWE-Rebench | 0.0% | estimated ± 6.5 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) | 27.1% | 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) | 39.3% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 70.0% | estimated ± 1.8 pp, low confidence |
| MMMU | 74.9% | estimated ± 0.9 pp, high confidence |
| MMLU | 89.0% | estimated ± 1.1 pp, medium confidence |
| MMMU-Pro w/ Python | 70.7% | estimated ± 1.6 pp, medium confidence |
| RealWorldQA | 77.9% | estimated ± 1.2 pp, low confidence |
| OmniDocBench 1.5 | 0.0% | estimated ± 6.4 pp, low confidence |