Meta · model
Muse Wonder Full benchmark scores
As of 2026-10-13, Muse Wonder Full (Meta) has measured scores on 16 benchmarks and estimated scores on 74 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 96.1% | estimated ± 2.1 pp, medium confidence |
| AA-HLE | 53.6% | measured |
| AA-SciCode | 62.6% | measured |
| Artificial Analysis Intelligence Index | 55.8% | measured |
| CritPt | 32.9% | measured |
| GDPval-AA | 67.9% | measured |
| GPQA Diamond | 95.7% | estimated ± 1.0 pp, medium confidence |
| HLE | 45.1% | estimated ± 9.5 pp, medium confidence |
| AA-LCR | 83.7% | measured |
| LiveCodeBench v6 | 100.0% | estimated ± 5.2 pp, low confidence |
| AA-Omniscience Accuracy | 43.2% | measured |
| SciCode | 62.0% | estimated ± 3.2 pp, medium confidence |
| Terminal-Bench 2.1 | 89.7% | estimated ± 3.9 pp, medium confidence |
| BrowseComp | 100.0% | estimated ± 6.2 pp, low confidence |
| HLE w/ tools | 65.7% | estimated ± 5.5 pp, medium confidence |
| AA Coding Index | 78.9% | estimated ± 2.5 pp, medium confidence |
| APEX-Agents | 52.2% | estimated ± 10.1 pp, low confidence |
| APEX-Agents-AA | 44.7% | estimated ± 3.6 pp, low confidence |
| BioMysteryBench (human-difficult) | 42.6% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 90.5% | estimated ± 8.5 pp, low confidence |
| SWE-bench Verified | 96.8% | estimated ± 5.2 pp, low confidence |
| AutomationBench | 35.6% | estimated ± 7.6 pp, low confidence |
| BFCL v4 | 77.8% | estimated ± 2.7 pp, medium confidence |
| CyberGym | 97.6% | estimated ± 6.2 pp, low confidence |
| JobBench | 75.3% | measured |
| SWE-bench Pro | 78.7% | estimated ± 6.8 pp, medium confidence |
| WideResearch | 86.8% | estimated ± 1.2 pp, low confidence |
| AA Agentic Index | 61.2% | estimated ± 2.8 pp, medium confidence |
| MMLU-Pro | 84.9% | estimated ± 3.7 pp, high confidence |
| GPQA | 95.7% | estimated ± 1.0 pp, medium confidence |
| Gert Labs | 100.0% | estimated ± 7.3 pp, low confidence |
| AA-AnalystAgent | 56.4% | estimated ± 8.7 pp, low confidence |
| AA EnterpriseOps-Gym | 58.2% | estimated ± 4.4 pp, medium confidence |
| ApprenticeBench | 21.3% | estimated ± 5.6 pp, low confidence |
| ARC-AGI-1 | 94.9% | estimated ± 5.4 pp, medium confidence |
| ARC-AGI-2 | 84.1% | estimated ± 14.2 pp, low confidence |
| CursorBench 3.1 | 75.1% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 52.4% | estimated ± 3.6 pp, medium confidence |
| FrontierCode 1.1 Main | 59.2% | estimated ± 3.7 pp, low confidence |
| FrontierSWE v2 | 48.7% | estimated ± 14.6 pp, low confidence |
| OSWorld-Verified | 91.5% | estimated ± 8.1 pp, low confidence |
| Vals GPQA Diamond | 98.1% | estimated ± 1.5 pp, low confidence |
| Vals LiveCodeBench | 77.4% | estimated ± 6.1 pp, low confidence |
| Vals MMLU-Pro | 91.5% | estimated ± 1.5 pp, low confidence |
| Vals SWE-bench | 95.1% | estimated ± 7.6 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 79.0% | estimated ± 8.5 pp, medium confidence |
| AA AutomationBench | 45.4% | measured |
| GDP.pdf | 32.6% | measured |
| AA Tau3 Banking | 47.4% | estimated ± 5.9 pp, low confidence |
| AA Terminal-Bench 2.1 | 86.8% | estimated ± 2.6 pp, high confidence |
| AA Terminal-Bench 4.0 | 57.1% | measured |
| Bug Hunt Bench | 33.0% | estimated ± 10.9 pp, low confidence |
| CursorBench 4.0 | 52.7% | estimated ± 3.5 pp, high confidence |
| CWE-bench v1 | 44.6% | estimated ± 6.0 pp, medium confidence |
| DeepSWE | 79.0% | measured |
| HLE w/o tools | 56.2% | estimated ± 5.7 pp, medium confidence |
| OSWorld 2.0 | 44.9% | estimated ± 13.3 pp, low confidence |
| PostTrainBench v1.1 | 47.4% | estimated ± 4.8 pp, medium confidence |
| ProgramBench | 59.0% | measured |
| Terminal-Bench 4.0 | 60.4% | estimated ± 5.1 pp, medium confidence |
| Terminal-Bench-Science 0.1 | 58.4% | estimated ± 4.1 pp, medium confidence |
| Toolathlon-Verified | 100.0% | estimated ± 1.3 pp, low confidence |
| ExploitGym | 44.2% | estimated ± 5.0 pp, low confidence |
| C-Eval | 93.4% | estimated ± 1.0 pp, low confidence |
| Claw-Eval | 66.2% | estimated ± 5.6 pp, low confidence |
| MCP Atlas | 82.3% | estimated ± 2.7 pp, medium confidence |
| MMLU-Redux | 96.6% | estimated ± 1.6 pp, medium confidence |
| NL2Repo | 69.9% | estimated ± 6.5 pp, low confidence |
| QwenClawBench | 94.0% | estimated ± 6.0 pp, low confidence |
| SuperGPQA | 81.8% | estimated ± 8.2 pp, medium confidence |
| Toolathlon | 55.9% | estimated ± 6.3 pp, low confidence |
| HealthBench Hard | 35.1% | estimated ± 7.7 pp, low confidence |
| MMLU-Pro (Arcee) | 100.0% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 82.0% | estimated ± 4.7 pp, low confidence |
| ResearchClawBench | 20.5% | estimated ± 2.2 pp, low confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, high confidence |
| Finance Agent v2 | 59.1% | measured |
| BioMysteryBench (human-solvable) | 89.5% | estimated ± 0.6 pp, low confidence |
| DRACO | 89.4% | estimated ± 3.1 pp, low confidence |
| HealthBench (raw) | 60.7% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 56.5% | estimated ± 2.2 pp, medium confidence |
| HealthBench Professional | 62.3% | measured |
| HealthBench Professional (raw) | 70.3% | estimated ± 5.0 pp, medium confidence |
| HLE-Verified | 37.7% | estimated ± 6.0 pp, low confidence |
| LABBench2 | 85.6% | estimated ± 2.4 pp, medium confidence |
| MMLU | 89.6% | estimated ± 3.9 pp, medium confidence |
| Agents' Last Exam | 59.5% | estimated ± 6.3 pp, low confidence |
| OpenHarmony Bench | 58.8% | estimated ± 2.4 pp, medium confidence |
| MRCRv2 | 85.9% | estimated ± 11.3 pp, low confidence |
| SWE-Marathon | 57.5% | measured |