Anthropic · model
Claude Mythos 5 benchmark scores
As of 2026-10-07, Claude Mythos 5 (Anthropic) has measured scores on 13 benchmarks and estimated scores on 82 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 93.6% | estimated ± 2.7 pp, high confidence |
| AA-HLE | 55.2% | estimated ± 5.0 pp, high confidence |
| AA-SciCode | 61.0% | estimated ± 3.8 pp, high confidence |
| Artificial Analysis Intelligence Index | 51.5% | estimated ± 5.1 pp, medium confidence |
| CritPt | 24.6% | estimated ± 4.1 pp, high confidence |
| GDPval-AA | 51.1% | estimated ± 5.1 pp, medium confidence |
| GPQA Diamond | 94.1% | estimated ± 0.4 pp, high confidence |
| HLE | 64.5% | measured |
| LiveCodeBench v6 | 96.2% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 51.2% | estimated ± 8.1 pp, medium confidence |
| SciCode | 55.3% | estimated ± 3.8 pp, medium confidence |
| Terminal-Bench 2.1 | 88.0% | measured |
| BrowseComp | 88.0% | measured |
| HLE w/ tools | 58.8% | estimated ± 4.6 pp, high confidence |
| VITA-Bench | 46.1% | estimated ± 9.9 pp, low confidence |
| AA Coding Index | 78.9% | estimated ± 5.1 pp, medium confidence |
| AA-MMMU-Pro | 82.9% | estimated ± 3.2 pp, medium confidence |
| APEX-Agents-AA | 37.8% | estimated ± 4.6 pp, high confidence |
| DeepSearchQA | 90.6% | estimated ± 8.1 pp, low confidence |
| SWE-bench Verified | 95.5% | measured |
| AutomationBench | 36.9% | estimated ± 5.8 pp, medium confidence |
| CyberGym | 83.8% | measured |
| JobBench | 52.4% | estimated ± 8.6 pp, low confidence |
| SWE-bench Pro | 80.3% | measured |
| WideResearch | 81.2% | estimated ± 4.6 pp, high confidence |
| AA Agentic Index | 48.5% | estimated ± 5.8 pp, medium confidence |
| MMLU-Pro | 86.0% | estimated ± 2.5 pp, low confidence |
| GPQA | 94.1% | measured |
| Gert Labs | 69.3% | estimated ± 6.0 pp, low confidence |
| AA-AnalystAgent | 39.6% | estimated ± 12.5 pp, low confidence |
| AA EnterpriseOps-Gym | 49.9% | estimated ± 5.9 pp, low confidence |
| AA Harvey LAB | 92.4% | estimated ± 9.8 pp, low confidence |
| ApprenticeBench | 24.2% | estimated ± 4.0 pp, medium confidence |
| ARC-AGI-1 | 97.4% | estimated ± 3.7 pp, high confidence |
| ARC-AGI-2 | 79.5% | estimated ± 11.6 pp, low confidence |
| CursorBench 3.1 | 66.9% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 71.4% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 23.0% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 53.2% | estimated ± 2.7 pp, medium confidence |
| FrontierSWE v2 | 51.3% | estimated ± 9.0 pp, medium confidence |
| OSWorld-Verified | 85.0% | measured |
| Vals GPQA Diamond | 94.4% | estimated ± 3.0 pp, high confidence |
| Vals LiveCodeBench | 88.5% | estimated ± 4.7 pp, medium confidence |
| Vals MMLU-Pro | 88.5% | estimated ± 1.2 pp, high confidence |
| Vals SWE-bench | 97.7% | estimated ± 6.8 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 73.9% | estimated ± 7.4 pp, medium confidence |
| AA AutomationBench | 46.4% | estimated ± 5.7 pp, low confidence |
| GDP.pdf | 12.2% | estimated ± 6.6 pp, low confidence |
| AA Tau3 Banking | 35.9% | estimated ± 10.2 pp, low confidence |
| AA Terminal-Bench 2.1 | 84.9% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 28.6% | estimated ± 8.9 pp, medium confidence |
| CursorBench 4.0 | 51.0% | estimated ± 3.6 pp, high confidence |
| HLE w/o tools | 59.0% | measured |
| OSWorld 2.0 | 20.4% | estimated ± 3.6 pp, high confidence |
| PostTrainBench v1.1 | 40.1% | estimated ± 4.7 pp, high confidence |
| SWE Multilingual | 92.2% | measured |
| Toolathlon-Verified | 73.5% | estimated ± 2.2 pp, low confidence |
| Vibe Code Bench | 62.5% | estimated ± 8.1 pp, low confidence |
| CharXiv | 93.5% | measured |
| CharXiv w/o tools | 88.9% | measured |
| ExploitBench | 78.0% | measured |
| ExploitGym | 25.3% | estimated ± 6.1 pp, low confidence |
| C-Eval | 93.3% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 81.7% | estimated ± 7.9 pp, low confidence |
| MathVision | 96.3% | estimated ± 2.1 pp, low confidence |
| MCP Atlas | 77.1% | estimated ± 10.0 pp, low confidence |
| MMLU-ProX | 91.1% | estimated ± 1.7 pp, low confidence |
| MMLU-Redux | 97.3% | estimated ± 2.1 pp, low confidence |
| MMMU-Pro | 82.3% | estimated ± 1.4 pp, low confidence |
| NL2Repo | 76.7% | estimated ± 6.1 pp, low confidence |
| NOVA-63 | 63.9% | estimated ± 1.6 pp, low confidence |
| ScreenSpot Pro | 89.8% | estimated ± 7.1 pp, medium confidence |
| SuperGPQA | 87.6% | estimated ± 9.1 pp, low confidence |
| Toolathlon | 55.9% | estimated ± 3.5 pp, high confidence |
| VideoMMMU | 88.2% | estimated ± 1.5 pp, high confidence |
| ERQA | 73.0% | estimated ± 3.7 pp, high confidence |
| HealthBench Hard | 36.4% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 97.4% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 80.4% | estimated ± 6.4 pp, low confidence |
| MedXpertQA (Text) | 74.6% | estimated ± 8.9 pp, low confidence |
| ResearchClawBench | 19.3% | estimated ± 2.2 pp, low confidence |
| SWE-Rebench | 61.8% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-3 | 2.8% | estimated ± 2.1 pp, high confidence |
| FrontierCode 1.1 Extended | 61.5% | estimated ± 3.0 pp, medium confidence |
| HealthBench Professional | 58.1% | estimated ± 4.8 pp, medium confidence |
| LiveCodeBench | 95.3% | estimated ± 10.2 pp, low confidence |
| Agents' Last Exam | 27.0% | estimated ± 2.1 pp, high confidence |
| OpenHarmony Bench | 60.9% | estimated ± 4.9 pp, low confidence |
| SEC-Bench Pro | 76.1% | estimated ± 4.3 pp, medium confidence |
| SimpleVQA | 73.6% | estimated ± 7.8 pp, low confidence |
| MMLU | 90.5% | estimated ± 3.6 pp, low confidence |
| MathVision w/ Python | 97.7% | estimated ± 0.9 pp, medium confidence |
| RealWorldQA | 88.0% | estimated ± 1.1 pp, medium confidence |
| Video-MME (with subtitle) | 90.1% | estimated ± 0.9 pp, medium confidence |
| OmniDocBench 1.5 | 92.7% | estimated ± 7.4 pp, low confidence |