Meta · model
Muse Ember benchmark scores
As of 2026-11-18, Muse Ember (Meta) has measured scores on 10 benchmarks and estimated scores on 55 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 73.6% | estimated ± 11.5 pp, low confidence |
| AA-HLE | 39.4% | estimated ± 9.2 pp, medium confidence |
| Artificial Analysis Intelligence Index | 36.0% | measured |
| CritPt | 15.5% | estimated ± 5.3 pp, medium confidence |
| GDPval-AA | 57.6% | estimated ± 4.2 pp, high confidence |
| GPQA Diamond | 91.9% | estimated ± 2.5 pp, high confidence |
| HLE | 26.5% | estimated ± 10.3 pp, low confidence |
| AA-Omniscience Accuracy | 21.1% | measured |
| Terminal-Bench 2.1 | 89.1% | estimated ± 5.4 pp, low confidence |
| BrowseComp | 77.6% | estimated ± 11.3 pp, low confidence |
| HLE w/ tools | 58.8% | estimated ± 4.9 pp, medium confidence |
| AA-MMMU-Pro | 82.1% | estimated ± 5.5 pp, medium confidence |
| BioMysteryBench (human-difficult) | 31.7% | estimated ± 7.8 pp, low confidence |
| AutomationBench | 47.1% | estimated ± 6.1 pp, low confidence |
| JobBench | 66.7% | estimated ± 11.3 pp, low confidence |
| MMLU-Pro | 84.1% | estimated ± 5.1 pp, medium confidence |
| GPQA | 92.1% | estimated ± 6.9 pp, medium confidence |
| MMLU | 89.3% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 90.7% | estimated ± 5.7 pp, medium confidence |
| Vals MMLU-Pro | 79.7% | estimated ± 2.9 pp, high confidence |
| MMMLU | 92.4% | estimated ± 3.0 pp, low confidence |
| AA MMLU-Pro | 84.2% | estimated ± 0.8 pp, medium confidence |
| ApprenticeBench | 13.1% | estimated ± 12.5 pp, low confidence |
| ARC-AGI-1 | 63.5% | estimated ± 7.9 pp, low confidence |
| ARC-AGI-2 | 64.9% | estimated ± 14.6 pp, low confidence |
| Terminal-Bench 3.0 | 27.2% | estimated ± 3.2 pp, high confidence |
| MazeBench | 0.0% | measured |
| ParseBench-1 | 69.1% | estimated ± 3.7 pp, high confidence |
| Terminal-Bench 4.1 | 30.6% | measured |
| Terminal-Bench Hard | 60.9% | estimated ± 2.8 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 75.8% | estimated ± 6.9 pp, low confidence |
| CWE-Bench-AA | 62.6% | estimated ± 9.0 pp, medium confidence |
| DeepsecBench-AA | 34.0% | estimated ± 7.5 pp, medium confidence |
| Harvey LAB-AA v1.1 | 4.3% | estimated ± 3.5 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 56.8% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 64.9% | estimated ± 1.1 pp, low confidence |
| CWE-bench v1 | 57.3% | estimated ± 5.3 pp, medium confidence |
| DRACO | 1.6% | estimated ± 0.7 pp, low confidence |
| HLE w/o tools | 44.7% | estimated ± 5.0 pp, high confidence |
| OSWorld 2.1 | 69.5% | measured |
| OSWorld 2.1 Offline | 35.0% | estimated ± 13.1 pp, low confidence |
| Terminal-Bench 4.0 | 40.9% | measured |
| Terminal-Bench-Science 0.1 | 15.1% | estimated ± 10.2 pp, low confidence |
| Toolathlon-Verified | 73.4% | estimated ± 2.6 pp, high confidence |
| AA AutomationBench | 68.1% | measured |
| GDP.pdf | 22.8% | measured |
| AA Terminal-Bench 4.0 | 40.9% | measured |
| CWE-bench | 54.1% | estimated ± 10.3 pp, low confidence |
| MKA | 46.2% | estimated ± 5.3 pp, medium confidence |
| Hermes Bench | 71.8% | estimated ± 1.8 pp, medium confidence |
| Hermes Index | 37.4% | estimated ± 2.7 pp, medium confidence |
| ParseBench-2 | 75.5% | measured |
| ExploitGym | 12.7% | estimated ± 6.4 pp, medium confidence |
| C-Eval | 96.3% | estimated ± 1.0 pp, low confidence |
| MMLU-Redux | 93.6% | estimated ± 0.8 pp, medium confidence |
| MMMU-Pro | 81.8% | estimated ± 5.4 pp, low confidence |
| SuperGPQA | 64.9% | estimated ± 9.3 pp, medium confidence |
| Finance Agent v2 | 56.1% | estimated ± 3.8 pp, medium confidence |
| HealthBench (length-adjusted) | 54.1% | estimated ± 3.7 pp, high confidence |
| HealthBench Professional | 57.4% | estimated ± 4.2 pp, medium confidence |
| HLE-Verified | 16.4% | estimated ± 7.1 pp, low confidence |
| STEMBench | 2.3% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 19.6% | estimated ± 4.3 pp, medium confidence |
| Agents' Last Exam | 35.3% | estimated ± 10.8 pp, low confidence |
| BioBasicsBench | 34.1% | estimated ± 3.8 pp, low confidence |