xAI · model
Grok 4.1 Fast benchmark scores
As of 2026-11-22, Grok 4.1 Fast (xAI) has measured scores on 13 benchmarks and estimated scores on 77 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 63.7% | measured |
| AA-HLE | 5.1% | measured |
| Artificial Analysis Intelligence Index | 11.3% | measured |
| CritPt | 0.0% | measured |
| GDPval-AA | 21.6% | estimated ± 10.5 pp, low confidence |
| GPQA Diamond | 69.5% | estimated ± 2.4 pp, high confidence |
| HLE | 16.9% | estimated ± 8.5 pp, medium confidence |
| IFBench | 53.9% | estimated ± 6.6 pp, low confidence |
| AA-LCR | 31.3% | measured |
| AA-Omniscience Accuracy | 17.2% | measured |
| BrowseComp | 69.0% | estimated ± 8.8 pp, medium confidence |
| HLE w/ tools | 48.1% | estimated ± 5.7 pp, medium confidence |
| IFEval | 87.6% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 51.2% | estimated ± 5.5 pp, medium confidence |
| τ²-bench results | 63.7% | measured |
| AA-MMMU-Pro | 48.4% | measured |
| APEX-Agents-AA | 14.3% | estimated ± 9.3 pp, medium confidence |
| BioMysteryBench (human-difficult) | 0.0% | estimated ± 6.8 pp, low confidence |
| BFCL v4 | 52.1% | estimated ± 8.5 pp, low confidence |
| CyberGym | 53.4% | estimated ± 11.0 pp, low confidence |
| JobBench | 21.8% | estimated ± 14.2 pp, low confidence |
| WideResearch | 70.4% | estimated ± 3.3 pp, high confidence |
| AA Agentic Index | 17.9% | estimated ± 9.4 pp, medium confidence |
| MMLU-Pro | 81.5% | estimated ± 5.0 pp, medium confidence |
| AA-IFBench | 36.5% | measured |
| FailureSensorIQ | 62.3% | estimated ± 1.7 pp, medium confidence |
| GPQA | 66.7% | estimated ± 6.1 pp, medium confidence |
| MMLU | 80.6% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 62.8% | estimated ± 3.2 pp, high confidence |
| Vals MMLU-Pro | 74.8% | estimated ± 2.9 pp, high confidence |
| MMMLU | 83.3% | estimated ± 0.7 pp, medium confidence |
| MMMU | 63.5% | estimated ± 2.7 pp, high confidence |
| Chess Puzzles | 19.3% | estimated ± 12.3 pp, low confidence |
| AA MMLU-Pro | 83.6% | estimated ± 0.8 pp, medium confidence |
| Gert Labs | 29.3% | measured |
| ApprenticeBench | 3.3% | estimated ± 10.4 pp, low confidence |
| ARC-AGI-1 | 74.7% | estimated ± 7.8 pp, low confidence |
| ARC-AGI-2 | 30.5% | estimated ± 14.4 pp, low confidence |
| MazeBench | 0.0% | estimated ± 2.7 pp, high confidence |
| Mystery Game Puzzles | 4.9% | estimated ± 2.2 pp, low confidence |
| NYT Connections | 12.3% | measured |
| OSWorld-Verified | 65.1% | estimated ± 8.6 pp, low confidence |
| ParseBench-1 | 42.0% | estimated ± 6.2 pp, low confidence |
| CWE-Bench-AA | 39.5% | estimated ± 8.1 pp, medium confidence |
| AA Cyber Index | 18.9% | estimated ± 12.4 pp, low confidence |
| DeepsecBench-AA | 8.9% | estimated ± 8.2 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 49.2% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 44.1% | estimated ± 1.1 pp, low confidence |
| AA ITBench | 36.7% | estimated ± 4.6 pp, medium confidence |
| CWE-bench v1 | 38.9% | estimated ± 5.7 pp, medium confidence |
| HLE w/o tools | 24.9% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.1 | 10.2% | estimated ± 3.6 pp, medium confidence |
| OSWorld 2.1 Offline | 39.2% | estimated ± 10.1 pp, low confidence |
| StealthMark | 41.3% | estimated ± 10.7 pp, low confidence |
| Toolathlon-Verified | 62.9% | estimated ± 3.0 pp, high confidence |
| AA AutomationBench | 42.8% | estimated ± 9.9 pp, low confidence |
| GDP.pdf | 13.2% | estimated ± 4.2 pp, medium confidence |
| ARC-AGI-3 | 1.3% | estimated ± 9.8 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| CWE-bench | 32.8% | estimated ± 6.2 pp, low confidence |
| MKA | 32.9% | estimated ± 4.6 pp, medium confidence |
| SkillsBench official leaderboard (BenchFlow) | 25.3% | estimated ± 6.1 pp, medium confidence |
| BinaryAudit | 7.0% | measured |
| OTelBench | 2.9% | measured |
| Hermes Index | 20.0% | estimated ± 5.7 pp, low confidence |
| ParseBench-2 | 34.4% | estimated ± 6.2 pp, low confidence |
| CharXiv | 61.0% | estimated ± 6.3 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 8.3 pp, low confidence |
| AI2D_TEST | 88.0% | estimated ± 2.0 pp, low confidence |
| C-Eval | 89.0% | estimated ± 1.0 pp, medium confidence |
| MMLU-Redux | 93.2% | estimated ± 0.8 pp, low confidence |
| MMMU-Pro | 48.6% | estimated ± 1.5 pp, high confidence |
| ScreenSpot Pro | 55.4% | estimated ± 10.8 pp, low confidence |
| SuperGPQA | 64.5% | estimated ± 9.3 pp, low confidence |
| Toolathlon | 37.8% | estimated ± 8.0 pp, medium confidence |
| Video-MME (w/o subtitle) | 71.2% | estimated ± 1.7 pp, low confidence |
| HealthBench Hard | 0.0% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 77.1% | estimated ± 4.0 pp, low confidence |
| Finance Agent v2 | 55.1% | estimated ± 2.4 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (length-adjusted) | 54.1% | estimated ± 3.7 pp, medium confidence |
| HealthBench Professional | 56.7% | estimated ± 4.2 pp, low confidence |
| STEMBench | 2.3% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 14.3% | estimated ± 4.3 pp, medium confidence |
| Agents' Last Exam | 29.6% | estimated ± 9.7 pp, low confidence |
| MRCRv2 | 22.8% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 56.5% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 14.1% | estimated ± 10.2 pp, low confidence |
| LifeVal | 6.1% | estimated ± 5.0 pp, low confidence |
| MMMU-Pro w/ Python | 54.3% | estimated ± 2.0 pp, medium confidence |