Gemini 4 Argon
Claude Opus 5.5
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview
Muse Wonder Full
Muse Wonder Full is a proprietary model from Meta. It ranks #4 of 27 on the Vals Index with 66.79%.
- Developer
- Meta
- Released
- —
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Proprietary
- Inputs
- —
- Reasoning
- —
- Tool use
- —
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| Vals IndexVals AI | 66.79% | 4 / 27 | $6.81 | |
| Terminal-Bench 4.0Coding | 58.08% | 6 / 55 | $10.53 | |
| Vibe Code BenchCoding | 86.00% | 13 / 115 | $2.29 | |
| Code MigrationCoding | 62.79% | 8 / 28 | $23.58 | |
| Finance AgentFinance | 67.58% | 3 / 31 | $2.68 | |
| Finance IndexFinance | 64.55% | 3 / 31 | $3.14 | |
| Tax Agent BenchFinance | 43.00% | 7 / 76 | $2.15 | |
| Legal IndexLaw | 77.86% | 1 / 28 | $3.72 | |
| Legal Research BenchLaw | 53.37% | 5 / 85 | $3.60 | |
| MedCodeMedicine | 49.93% | 18 / 107 | $4 / $20 | |
| Terminal-Bench ScienceReasoning | 37.14% | 7 / 42 | $22.81 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| WebDevLMArena | 1726 | 6 / 124 | 2.3K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Muse Wonder Full
Meta
Meta’s AI research publishes the Llama family, among the most downloaded open-weight models. Founded 2013 (FAIR), based in Menlo Park. ai.meta.com
Questions
Who makes Muse Wonder Full?
Muse Wonder Full is made by Meta, founded 2013 (FAIR) and based in Menlo Park.
Is Muse Wonder Full open source?
No. Muse Wonder Full is proprietary and served through its provider’s API.