- Personal Superintelligence Index (internal composite) 59.1
- Harvey LAB-AA 13.1
- Vals Finance Agent V2 59.1
- HealthBench Pro 62.3
- AutomationBench-AA 45.4
- GDP.pdf 33.2
- JobBench 75.3
- OSWorld V2.1 (partial; binary 39.4) 78.4
- MemoryBench 85.5
- Terminal-Bench 4.0-AA 57.1
- DeepSWE 1.1 79
- SWE-Marathon (xhigh) (version not stated) 57.5
- ProgramBench 59
- Artificial Analysis Index 56
- FocusBench (chart label) 54.2
Muse Wonder Full
Muse Wonder Full ranks first on 7 of the 54 benchmarks it has scores on.
62
Benchmarks with a score
7
Ranked first, out of five or more models
19
In the top three
Meta Oct 2026 Muse Wonder Full
Closed weights Flagship
No Epoch Capabilities Index score yet
- HealthBench Professional 62.3% #10 /25
- Harvey LAB (Legal Agent Benchmark) 21.7% #3 /80
- ProgramBench 8.50% #3 /25
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ProofBench v1.1 | 94% | #9 of 51 | Official leaderboard | |
| MysteryMechanism | 35.1% | #11 of 29 | Official leaderboard | |
| CritPt v2 | 73.1% | #5 of 11 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| DeepSWE | 79% | #1 of 51 | Model card | |
| Vibe Code Bench 1-100 | 34% | #1 of 26 | Official leaderboard | |
| Code Arena | 1,725 | #7 of 124 | Official leaderboard | |
| SWE-Marathon v1.1 | 53.1% | #1 of 17 | Official leaderboard | |
| Code Migration | 61% | #7 of 78 | Official leaderboard | |
| ProgramBench | 8.50% | #3 of 25 | Official leaderboard | |
| Vibe Code Bench | 86% | #14 of 115 | Official leaderboard | |
| SWE-Marathon | 57.5% | #2 of 11 | Model card | |
| IOI v2 (Vals) | 79.8% | #12 of 45 | Official leaderboard | |
| Code Migration v1.1 | 62.8% | #8 of 29 | Official leaderboard | |
| Vals RSI Index | 0.24 | #9 of 25 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LisanBench | 37152.2 | #1 of 133 | Official leaderboard | |
| Agent Arena | 0.10 | #9 of 53 | Official leaderboard | |
| AutomationBench | 45.4% | #13 of 41 | Model card | |
| Terminal-Bench 4.0 | 57.1% | #8 of 23 | Model card | |
| FocusBench (Meta) | 54.2% | #1 of 2 | Model card | |
| StarSkirmish Bench | 21.4% | #7 of 9 | Official leaderboard | |
| OSWorld 2.1 | 78.4% | #4 of 5 | Model card |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LegalBench | 87.4% | #4 of 138 | Official leaderboard | |
| Vals Legal Index | 77.9% | #1 of 33 | Official leaderboard | |
| Harvey LAB (Legal Agent Benchmark) | 21.7% | #3 of 80 | Official leaderboard | |
| Public Benefits Bench | 73.8% | #3 of 50 | Official leaderboard | |
| Legal Research Bench | 53.4% | #6 of 88 | Official leaderboard | |
| Vals Finance Agent v2 | 59.1% | #6 of 80 | Official leaderboard | |
| Vending-Bench 2 | $12,292 | #5 of 66 | Official leaderboard | |
| MedScribe | 89.3% | #8 of 98 | Official leaderboard | |
| JobBench | 75.3% | #1 of 12 | Model card | |
| Vals Finance Agent v2.1 | 67.6% | #3 of 35 | Official leaderboard | |
| Tax Agent Bench | 43% | #8 of 79 | Official leaderboard | |
| Vals Finance Index | 64.5% | #4 of 35 | Official leaderboard | |
| Harvey LAB v1.1 (HLAB-Vals-1.1) | 23.3% | #4 of 33 | Official leaderboard | |
| Immigration Bench | 71.2% | #3 of 24 | Official leaderboard | |
| Excel Modeling Benchmark | 71.9% | #10 of 76 | Official leaderboard | |
| Excel Modeling Benchmark v1.1 | 75% | #5 of 37 | Official leaderboard | |
| Vals Index v2.2 | 66.8% | #5 of 32 | Official leaderboard | |
| MedCode | 49.9% | #18 of 96 | Official leaderboard | |
| HealthBench Professional | 62.3% | #10 of 25 | Model card |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GDP.pdf | 33.2% | #7 of 15 | Model card | |
| Robo-bench | 10.4% | #4 of 7 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CyberGym | 88.4% | #3 of 33 | Model card | |
| LAB-Bench ProtocolQA | 89% | #2 of 15 | Model card | |
| BioTIER | 98.7% | #1 of 5 | Model card | |
| LAB-Bench SeqQA | 95.6% | #3 of 12 | Model card | |
| Human Pathogen Capabilities Test | 66.5% | #2 of 8 | Model card | |
| ABC Bench Liquid-Handling Robot | 100.0 | #1 of 4 | Model card | |
| Meta BioDesign Proxy | 79.4 | #1 of 4 | Model card | |
| Meta chemical-agent refusal evaluation | 100% | #1 of 4 | Model card | |
| CyberBench v1.1 (Vals) | 73.6% | #11 of 43 | Official leaderboard | |
| Agentic misalignment suite (Anthropic) | 0% | #2 of 7 | Model card | |
| Molecular Biology Capabilities Test | 59.6% | #2 of 7 | Model card | |
| SRE-Bench | 11.8% | #10 of 33 | Official leaderboard | |
| CyberBench (Liu et al.) | 0.80% | #1 of 3 | Model card | |
| Poly-Guard Bench | 2.30% | #1 of 3 | Model card | |
| Virology Capabilities Test (VCT) | 55.9% | #11 of 28 | Model card | |
| ExploitBench | 58.9% | #10 of 19 | Model card | |
| MASK | 87.3% | #13 of 21 | Model card | |
| RedCode | 8.00% | #2 of 3 | Model card |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Artificial Analysis Intelligence Index v4.3 | 56.0 | #1 of 4 | Model card | |
| Vals Science Index | 48.5% | #6 of 23 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 19 of them aren't in the launch post.
Muse Wonder Model Card 12 Oct 2026
Capabilities
- Personal Superintelligence Index (Meta) 59.1
- Harvey LAB (Legal Agent Benchmark) 13.1
- Vals Finance Agent v2 59.1
- AutomationBench 45.4
- GDP.pdf 33.2
- JobBench 75.3
- OSWorld 2.1 78.4
- MemoryBench (Meta) 85.5
- Terminal-Bench 4.0 57.1
- DeepSWE 79
- SWE-Marathon 57.5
- ProgramBench 59
- Artificial Analysis Intelligence Index v4.3 56
Health
Alignment
Bio and chem risk
- Molecular Biology Capabilities Test 59.6
- Human Pathogen Capabilities Test 66.5
- Virology Capabilities Test (VCT) 55.9
- LAB-Bench ProtocolQA 89
- LAB-Bench SeqQA 95.6
- ABC Bench Fragment Design
- ABC Bench Liquid-Handling Robot 100
- ABC Bench Screening Evasion
- Meta BioDesign Proxy 79.4
- BioTIER 98.7
- Meta chemical-agent refusal evaluation 100
Cyber risk
- CyberGym 88.4
- ExploitBench 58.9
- ExploitGym 20
- CyberBench (Liu et al.) 0.8
- Poly-Guard Bench 2.3
- RedCode 8