Muse Wonder
Muse WonderMetaProprietaryReasoningProvisionalReleased Oct 12, 2026Input: text, image, video, file, audio
Overall score
71.5
Rank 14 of 222 · 57.1–85.8
Context window
1M
1,000,000 tokens
Price per 1M tokens
$4.00 in · $20.00 out
Source: BenchLM
Blended price
$8.00
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
Benchmark results (9)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Coding
| DeepSWE | 78.8 | #2 of 50 |
| Bug Hunt Bench | 31.7 | #11 of 23 |
| ProgramBench | 50.0 | #10 of 15 |
Agentic & tool use
| MazeBench | 0 | #20 of 42 |
| JobBench | 70.5 | #2 of 34 |
Reasoning
| STEMBench | 2.68 | #3 of 9 |
Multimodal
| Design Arena Website | 1360 | #1 of 91 |
Knowledge
| HealthBench Professional | 60.5 | #9 of 16 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price (BenchLM) | $4.00 | $20.00 | $0.20 |
| OpenRouter meta/muse-wonder | $4.00 | $20.00 | $0.20 |
Meta lists muse-wonder-1.0 at $4 input, $0.20 cached input, and $20 output per million tokens, with a 1M-token context window. Available on Meta Model API and Muse Code.
Arena ratings
Human-preference ratings from LMArena. Best-rated variant shown.
| Text(Max) | 1501 | #7 · 3.2K votes |
| WebDev (coding)(Max) | 1652 | #17 · 2.3K votes |
Speed
Measured by us through OpenRouter (median of trials).
Not measured yet.
Related models
Same family
- Muse Wonder Full74.8
Similar score
- GPT-5.6 Terra70.2 · $4.50
- Claude Opus 4.870.0 · $10.00
- Kimi K370.0 · $6.00
- Qwen3.8 Max69.7 · —
- Step 5 Preview69.6 · $1.43