Muse Glimmer
Meta AI🇺🇸 United States
Context window131K tokens
Input / 1M tokens$0.35
Output / 1M tokens$1.5
Pricing and context window via OpenRouter.
Version History
1.0major
Meta's first open-weight model since Llama 4 (spring 2025), a 30B-parameter agent model released under Apache 2.0, distilled from the larger Muse Spark model and optimized for local, on-device execution.
30Bmajor
New 29.6B-parameter open-weight model with a built-in perception encoder, distilled from Muse Spark, designed for on-device agentic use with 4-bit quantization and speculative decoding.
Benchmark Scores
Full leaderboard →| Benchmark | Score | Rank | Source |
|---|---|---|---|
| AA Intelligence Index | 6.3 index | 117 of 124 | Artificial Analysis, Nov 2026 ↗ |
| Arena Elo | 1424 Elo | 80 of 151 | LMArena, Nov 2026 ↗ |
| GPQA | 83.5% | 94 of 159 | Artificial Analysis, Aug 2026 ↗ |
| SWE-bench Verified | 76.0% | 34 of 78 | Hugging Face model card ↗ |
| AA Coding Index | 49 index | 50 of 78 | Artificial Analysis, Oct 2026 ↗ |
| Speed (tok/s) | 119 tok/s | 56 of 127 | Artificial Analysis, Nov 2026 ↗ |
| Hallucination Rate (lower is better) | 81.9% | 75 of 109 | Artificial Analysis, Aug 2026 ↗ |
| AIME 2026 | 94.7% | 10 of 26 | Hugging Face model card ↗ |
Rank is against every model in our database with a sourced score on that benchmark, each counted once with its best score.