xAI · model
Grok 4.5 benchmark scores
As of 2026-10-07, Grok 4.5 (xAI) has measured scores on 27 benchmarks and estimated scores on 81 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 93.1% | measured |
| AA-HLE | 42.7% | measured |
| AA-SciCode | 55.0% | measured |
| Artificial Analysis Intelligence Index | 38.8% | measured |
| CritPt | 15.4% | measured |
| GDPval-AA | 44.5% | measured |
| GPQA Diamond | 89.5% | estimated ± 1.4 pp, high confidence |
| HLE | 55.0% | estimated ± 5.5 pp, low confidence |
| AA-LCR | 79.3% | measured |
| LiveCodeBench v6 | 91.6% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 51.6% | measured |
| SciCode | 51.5% | estimated ± 2.9 pp, medium confidence |
| Terminal-Bench 2.1 | 83.3% | measured |
| BrowseComp | 84.2% | estimated ± 9.0 pp, medium confidence |
| HLE w/ tools | 54.4% | estimated ± 6.1 pp, medium confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, low confidence |
| τ²-bench results | 94.1% | estimated ± 13.3 pp, low confidence |
| AA Coding Index | 72.5% | measured |
| AA-MMMU-Pro | 80.4% | measured |
| APEX-Agents | 37.5% | estimated ± 10.0 pp, low confidence |
| APEX-Agents-AA | 33.5% | estimated ± 9.1 pp, medium confidence |
| BioMysteryBench (human-difficult) | 46.3% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 92.1% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 85.8% | estimated ± 2.5 pp, high confidence |
| AutomationBench | 28.4% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 77.0% | estimated ± 2.6 pp, medium confidence |
| CyberGym | 77.9% | estimated ± 5.3 pp, medium confidence |
| JobBench | 45.2% | estimated ± 8.6 pp, medium confidence |
| SWE-bench Pro | 64.7% | measured |
| WideResearch | 95.0% | estimated ± 9.1 pp, low confidence |
| AA Agentic Index | 42.1% | measured |
| MMLU-Pro | 85.7% | estimated ± 3.5 pp, medium confidence |
| GPQA | 93.2% | estimated ± 0.8 pp, high confidence |
| Gert Labs | 74.0% | estimated ± 8.5 pp, medium confidence |
| AA-AnalystAgent | 34.9% | estimated ± 12.0 pp, low confidence |
| AA EnterpriseOps-Gym | 42.7% | estimated ± 6.7 pp, low confidence |
| AA Harvey LAB | 92.6% | estimated ± 1.2 pp, medium confidence |
| ARC-AGI-1 | 85.7% | measured |
| ARC-AGI-2 | 52.6% | measured |
| CursorBench 3.1 | 56.3% | estimated ± 3.4 pp, medium confidence |
| CursorBench 3.2 | 66.7% | measured |
| Terminal-Bench 3.0 | 15.7% | measured |
| FrontierCode 1.1 Main | 49.9% | estimated ± 1.6 pp, medium confidence |
| FrontierSWE v2 | 23.5% | estimated ± 9.0 pp, medium confidence |
| OfficeQA Pro | 59.6% | estimated ± 7.2 pp, medium confidence |
| OSWorld-Verified | 78.9% | estimated ± 8.7 pp, low confidence |
| Vals GPQA Diamond | 92.9% | measured |
| Vals LiveCodeBench | 87.4% | measured |
| Vals MMLU-Pro | 89.2% | measured |
| Vals SWE-bench | 86.6% | measured |
| Terminal-Bench 2.1 (Vals AI) | 67.8% | measured |
| VulcanBench v3 | 89.9% | measured |
| AA AutomationBench | 49.3% | estimated ± 7.0 pp, medium confidence |
| GDP.pdf | 10.2% | estimated ± 5.4 pp, medium confidence |
| AA Tau3 Banking | 42.5% | estimated ± 5.8 pp, medium confidence |
| AA Terminal-Bench 2.1 | 84.8% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 22.6% | estimated ± 8.9 pp, medium confidence |
| CursorBench 4.0 | 35.7% | estimated ± 1.6 pp, high confidence |
| CWE-bench v1 | 52.0% | estimated ± 6.9 pp, medium confidence |
| DeepSWE | 53.0% | measured |
| HLE w/o tools | 44.5% | estimated ± 5.0 pp, medium confidence |
| PostTrainBench v1.1 | 23.5% | measured |
| ProgramBench | 0.0% | estimated ± 4.8 pp, low confidence |
| SWE Multilingual | 78.0% | measured |
| Toolathlon-Verified | 69.5% | estimated ± 2.3 pp, medium confidence |
| Vibe Code Bench | 59.4% | estimated ± 10.3 pp, low confidence |
| CharXiv | 85.8% | estimated ± 7.5 pp, low confidence |
| CharXiv w/o tools | 82.9% | estimated ± 2.4 pp, high confidence |
| ExploitGym | 18.2% | estimated ± 12.2 pp, low confidence |
| C-Eval | 95.5% | estimated ± 1.0 pp, low confidence |
| Claw-Eval | 80.7% | estimated ± 13.6 pp, low confidence |
| MathVision | 89.7% | estimated ± 4.9 pp, high confidence |
| MCP Atlas | 78.7% | estimated ± 7.8 pp, low confidence |
| MMLU-ProX | 85.9% | estimated ± 1.7 pp, medium confidence |
| MMLU-Redux | 97.5% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro | 79.4% | estimated ± 4.4 pp, medium confidence |
| NL2Repo | 50.8% | estimated ± 4.7 pp, high confidence |
| NOVA-63 | 58.4% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 100.0% | estimated ± 6.0 pp, low confidence |
| ScreenSpot Pro | 79.6% | estimated ± 10.7 pp, low confidence |
| SuperGPQA | 86.3% | estimated ± 7.5 pp, low confidence |
| Terminal-Bench 2.0 | 72.1% | estimated ± 5.9 pp, medium confidence |
| Toolathlon | 55.9% | estimated ± 6.3 pp, medium confidence |
| ERQA | 68.5% | estimated ± 3.9 pp, high confidence |
| HealthBench Hard | 33.1% | estimated ± 7.7 pp, low confidence |
| LiveCodeBench Pro | 87.3% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 77.1% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 100.0% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 93.1% | estimated ± 2.4 pp, low confidence |
| ResearchClawBench | 20.3% | estimated ± 2.0 pp, high confidence |
| SWE-Rebench | 58.1% | estimated ± 8.9 pp, low confidence |
| ARC-AGI-3 | 0.3% | measured |
| BioMysteryBench (human-solvable) | 87.8% | estimated ± 0.6 pp, medium confidence |
| DRACO | 79.8% | estimated ± 3.0 pp, medium confidence |
| FrontierCode 1.1 Extended | 59.4% | estimated ± 1.6 pp, medium confidence |
| HealthBench (raw) | 51.5% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.8% | estimated ± 0.9 pp, medium confidence |
| HealthBench Professional | 59.9% | estimated ± 1.3 pp, medium confidence |
| HealthBench Professional (raw) | 61.7% | estimated ± 5.0 pp, medium confidence |
| HLE-Verified | 35.3% | estimated ± 0.7 pp, low confidence |
| LABBench2 | 63.1% | estimated ± 1.3 pp, low confidence |
| MMMU | 87.6% | estimated ± 0.9 pp, medium confidence |
| LiveCodeBench | 100.0% | estimated ± 8.9 pp, low confidence |
| OpenHarmony Bench | 58.8% | estimated ± 2.4 pp, high confidence |
| MMLU | 95.1% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro w/ Python | 82.0% | estimated ± 1.6 pp, high confidence |
| RealWorldQA | 87.8% | estimated ± 1.2 pp, medium confidence |
| OmniDocBench 1.5 | 92.0% | estimated ± 6.4 pp, low confidence |