- Personal Superintelligence Index (internal composite) 54.3
- Harvey LAB-AA 10
- Vals Finance Agent V2 56.6
- HealthBench Pro 60.5
- AutomationBench-AA 39.1
- GDP.pdf 30.8
- JobBench 70.5
- OSWorld V2.1 (partial; binary 34.3) 72.6
- MemoryBench 85.6
- Terminal-Bench 4.0-AA 52
- DeepSWE 1.1 78.8
- SWE-Marathon (version not stated) 53.1
- ProgramBench 50
- Artificial Analysis Index 52
- FocusBench (chart label) 44.9
Muse Wonder
Muse Wonder ranks first on 2 of the 93 benchmarks it has scores on.
Meta Released 12 Oct 2026 95
Benchmarks with a score
2
Ranked first, out of five or more models
17
In the top three
Meta Oct 2026 Muse Wonder
Closed weights
161.7
#13 of 271
Epoch Capabilities Index
- Agents' Last Exam 38.5% #7 /12
- HealthBench Professional 60.5% #15 /25
- Harvey LAB (Legal Agent Benchmark) 17.1% #7 /80
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.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMArena (Elo) | 1,507 | #4 of 333 | Official leaderboard | |
| Creative Writing v3 | 81.1 | #7 of 120 | Official leaderboard | |
| EQ-Bench 4 | 1,325 | #3 of 32 | Official leaderboard | |
| Extended NYT Connections | 93.4% | #12 of 97 | Official leaderboard | |
| BullshitBench V2 | 57.6% | #35 of 122 | Official leaderboard | |
| HLE-Diamond | 40.6% | #9 of 18 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.4% | #16 of 202 | Epoch AI | |
| CritPt | 28.3% | #14 of 160 | Epoch AI | |
| DTBench | 92% | #22 of 178 | Official leaderboard | |
| ProofBench | 84% | #12 of 83 | Epoch AI | |
| FrontierMath Tiers 1-3 v2 | 82.1% | #17 of 89 | Epoch AI | |
| FrontierMath Tier 4 v2 | 70.7% | #16 of 71 | Epoch AI | |
| ProofBench v1.1 | 84% | #13 of 51 | Official leaderboard | |
| MysteryMechanism | 27.5% | #15 of 29 | Official leaderboard | |
| CritPt v2 | 69.7% | #8 of 11 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| DeepSWE | 78.8% | #2 of 51 | Model card | |
| Code Migration | 62.5% | #6 of 78 | Official leaderboard | |
| SWE-Marathon v1.1 | 52.5% | #2 of 17 | Official leaderboard | |
| Code Arena | 1,652 | #18 of 124 | Official leaderboard | |
| ProgramBench | 5.50% | #4 of 25 | Official leaderboard | |
| Code Migration v1.1 | 72.4% | #5 of 29 | Official leaderboard | |
| Vibe Code Bench | 83.1% | #22 of 115 | Official leaderboard | |
| Vibe Code Bench 1-100 | 26.6% | #6 of 26 | Official leaderboard | |
| CursorBench | 50.4% | #5 of 19 | Epoch AI | |
| SWE-Marathon | 53.1% | #3 of 11 | Model card | |
| SWE-Bench Pro V2 Hard | 90.2% | #5 of 16 | Official leaderboard | |
| IOI v2 (Vals) | 66.9% | #16 of 45 | Official leaderboard | |
| SWE-Bench Pro V2 | 96.7% | #6 of 16 | Official leaderboard | |
| WeirdML v3 | 15.2% | #11 of 25 | Official leaderboard | |
| MirrorCode | 45.6% | #14 of 28 | Epoch AI | |
| FrontierCode 2.0 | 24.3% | #13 of 26 | Official leaderboard | |
| FrontierCS 2 | 20.8% | #10 of 16 | Official leaderboard | |
| Web Clone Bench | 3.70% | #6 of 9 | Official leaderboard | |
| OpenDesign Arena | 76.2 | #15 of 19 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LisanBench | 27973.3 | #2 of 133 | Official leaderboard | |
| Mystery Game Puzzles | 51% | #13 of 80 | Epoch AI | |
| Agent Arena | 0.03 | #15 of 53 | Official leaderboard | |
| Terminal-Bench 4.0 | 52% | #9 of 23 | Model card | |
| AutomationBench | 39.1% | #19 of 41 | Model card | |
| EBR-bench | 31.4% | #13 of 28 | Epoch AI | |
| CUA-bench | 7.17% | #6 of 9 | Official leaderboard | |
| OSWorld 2.1 | 72.6% | #5 of 5 | Model card | |
| FocusBench (Meta) | 44.9% | #2 of 2 | Model card |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| TaxCalcBench v2 | 77.5% | #1 of 26 | Official leaderboard | |
| PRBench | 58.4% | #3 of 44 | Official leaderboard | |
| Harvey LAB (Legal Agent Benchmark) | 17.1% | #7 of 80 | Official leaderboard | |
| Legal Research Bench | 50.5% | #8 of 88 | Official leaderboard | |
| Harvey LAB v1.1 (HLAB-Vals-1.1) | 23.8% | #3 of 33 | Official leaderboard | |
| Legora BAR | 105.0 | #2 of 17 | Official leaderboard | |
| Public Benefits Bench | 70.2% | #6 of 50 | Official leaderboard | |
| Vals Legal Index | 75.3% | #4 of 33 | Official leaderboard | |
| APEX-Agents | 66.1% | #8 of 56 | Epoch AI | |
| Tax Agent Bench | 36.3% | #13 of 79 | Official leaderboard | |
| Vending-Bench 2 | $9,432 | #11 of 66 | Official leaderboard | |
| JobBench | 70.5% | #2 of 12 | Model card | |
| PharmaBench (micro1) | 17.2% | #2 of 12 | Official leaderboard | |
| FrontierFinance | 52.6% | #3 of 16 | Official leaderboard | |
| Vals Finance Agent v2.1 | 65.5% | #7 of 35 | Official leaderboard | |
| Vals Finance Index | 61.2% | #7 of 35 | Official leaderboard | |
| Immigration Bench | 69.6% | #5 of 24 | Official leaderboard | |
| Vals Index v2.2 | 64.9% | #7 of 32 | Official leaderboard | |
| PolicyBench | 90% | #11 of 50 | Official leaderboard | |
| Vals Finance Agent v2 | 56.6% | #18 of 80 | Official leaderboard | |
| Excel Modeling Benchmark | 67.1% | #19 of 76 | Official leaderboard | |
| micro1 Medical Index | 70.8% | #2 of 8 | Official leaderboard | |
| Excel Modeling Benchmark v1.1 | 72.5% | #10 of 37 | Official leaderboard | |
| EEBench | 62.7% | #8 of 26 | Official leaderboard | |
| RealmPathology | 76.4% | #4 of 13 | Official leaderboard | |
| MissionReport | 62.1% | #5 of 9 | Official leaderboard | |
| Agents' Last Exam | 38.5% | #7 of 12 | Official leaderboard | |
| HealthBench Professional | 60.5% | #15 of 25 | Model card | |
| RWE-bench | 0% | #11 of 11 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GDP.pdf | 30.8% | #4 of 39 | Epoch AI | |
| Humanity's Sixth Sense | 43.7% | #5 of 29 | Official leaderboard | |
| VoxelBench | 1,872 | #17 of 56 | Official leaderboard | |
| Furniture Assembly Benchmark | 54.2% | #12 of 35 | Epoch AI | |
| DataCenterBench Tier 1 | 16.7% | #5 of 9 | Official leaderboard | |
| Dual-Arm Sim | 9.50 | #8 of 10 | Official leaderboard | |
| RoboColiseum | 42.3% | #8 of 9 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CyberBench v1.1 (Vals) | 80.4% | #1 of 43 | Official leaderboard | |
| DistressBench | 85.9% | #3 of 42 | Official leaderboard | |
| BioSecBench-Refusal | 55.3% | #2 of 22 | Official leaderboard | |
| PCT (Polarized Contrastive Pairs) | 33.3% | #5 of 46 | Official leaderboard | |
| OncologyBench | 24% | #8 of 30 | Official leaderboard | |
| CheatBench | 12.7% | #3 of 10 | Official leaderboard | |
| WellnessBench | 55% | #7 of 12 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CAIS Risk Index | 32.4 | #5 of 65 | Official leaderboard | |
| LMCA | 56.8% | #12 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 67.7 | #13 of 149 | Official leaderboard | |
| CAIS Vision Capabilities Index | 71.2 | #5 of 53 | Official leaderboard | |
| ACCoRD | 76.2 | #22 of 150 | Official leaderboard | |
| CAIS Text Capabilities Index | 47.6 | #11 of 66 | Official leaderboard | |
| LiveBench | 74.2% | #8 of 28 | Official leaderboard | |
| Vals Science Index | 39.1% | #11 of 23 | Official leaderboard | |
| Artificial Analysis Intelligence Index v4.3 | 52.0 | #2 of 4 | Model card |
Meta's models over time
Meta's models in color, against every other model on the Epoch Capabilities Index, by release date.
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.
Muse Wonder Model Card 12 Oct 2026
Capabilities
- Personal Superintelligence Index (Meta) 54.3
- Harvey LAB (Legal Agent Benchmark) 10
- Vals Finance Agent v2 56.6
- AutomationBench 39.1
- GDP.pdf 30.8
- JobBench 70.5
- OSWorld 2.1 72.6
- MemoryBench (Meta) 85.6
- Terminal-Bench 4.0 52
- DeepSWE 78.8
- SWE-Marathon 53.1
- ProgramBench 50
- Artificial Analysis Intelligence Index v4.3 52