Muse Wonder
Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.
Shogo Agent Index
Estimated#15 of 9260.9range 51.9–69.9 · 22% of weight measured
Agentic coding
68
11% measured
Long-horizon autonomy
70
50% measured
Knowledge-work agents
50
32% measured
Computer use
50
estimated
Security & context learning
57
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 84 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 89 | |
| DeepSWE | est. | 6% | predicted 67 | |
| FrontierSWE | est. | 5% | predicted 36 | |
| CursorBench | 50.4% | 4% | source · $5.25/task | |
| GSO-Bench | est. | 4% | predicted 54 | |
| METR Time Horizons | est. | 10% | predicted 82 | |
| Vending-Bench 2 | $9,432 | 6% | source | |
| PostTrainBench | 24.2% | 4% | OpenCode | |
| APEX-Agents | 66.1% | 8% | source | |
| GDPval | est. | 7% | predicted 60 | |
| Remote Labor Index | est. | 5% | predicted 10 | |
| DeepResearch Bench | est. | 5% | predicted 51 | |
| OSWorld 2.0 | est. | 6% | predicted 23 | |
| OSWorld | est. | 4% | predicted 89 | |
| Cybench | est. | 5% | predicted 87 | |
| CL-bench | est. | 5% | predicted 26 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| CritPt | Reasoning | 28.3% | source |
| DTBench | Knowledge | 95.2% | source |
| FrontierMath Tiers 1-3 | Math | 82.1% | source |
| FrontierMath Tier 4 | Math | 70.7% | source |
| LMCA | Knowledge | 56.8% | source |
| MirrorCode | Coding | 45.6% | source |
| OTIS Mock AIME | Math | 99.4% | source |
| ProofBench | Math | 84.0% | source |
| SciCode | Coding | 60.3% | source |
| WeirdML v3 | Coding | 15.1% | codex_cli |