# Muse Glimmer 30B Benchmark Scores & Performance

> Muse Glimmer 30B by Meta scores 41.73/100 overall, ranking #108 out of 507 AI models.

Canonical page: https://benchlm.ai/models/muse-glimmer-30b

Last updated: September 24, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Meta |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 131K |
| Overall Score | 41.73/100 |
| Overall Rank | #108 of 507 |

## Family & Coverage

- Family: Muse Glimmer
- Variant: 30b (30B)
- Benchmarks covered: 30 of 483
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [MCP Atlas](/benchmarks/mcpatlas) | 75.5% |
| [DeepSearchQA](/benchmarks/deepsearchqa) | 74.6% |
| [skillsBench](/benchmarks/skillsbench) | 44.3% |
| [OSWorld-Verified](/benchmarks/osworld-verified) | 65.9% |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 13.7% |
| [AA EnterpriseOps-Gym](/benchmarks/aaenterpriseopsgym) | 34.7% |
| [AA Agentic Index](/benchmarks/aaagenticindex) | 10.5% |
| [GDPval-AA](/benchmarks/gdpvalaa) | 893 |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 51.2% |
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 76% |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 51.7% |
| [SciCode](/benchmarks/scicode) | 43.6% |
| [AA-SciCode](/benchmarks/aascicode) | 44.9% |
| [AA Coding Index](/benchmarks/aacodingindex) | 49.0% |

## Multimodal & Grounded Benchmarks

| Benchmark | Score |
|-----------|-------|
| [CharXiv](/benchmarks/charxiv) | 78.8% |
| [ScreenSpot Pro](/benchmarks/screenspot-pro) | 75.4% |
| [OmniDocBench 1.5](/benchmarks/omnidocbench15) | 75.8% |
| [MMMU-Pro](/benchmarks/mmmu-pro) | 74% |
| [AA-MMMU-Pro](/benchmarks/aammmupro) | 74.3% |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 83.3% |
| [CritPt](/benchmarks/critpt) | 2.6% |
| [MLCR-AA](/benchmarks/aamlcr) | 20.0% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 17.5% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 83.5% |
| [AA-HLE](/benchmarks/aahle) | 22.0% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -32.8% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 27.0% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 81.9% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [IFBench](/benchmarks/ifbench) | 77% |

## Mathematics Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AIME26](/benchmarks/aime2026) | 94.7% |

## Other Meta Models

- [Muse Spark 1.1](/models/muse-spark-1-1) - Score: 65.92
- [Muse Spark 1.2](/models/muse-spark-1-2) - Score: 64.99
- [Muse Spark](/models/muse-spark) - Score: 60.81
- [Llama 3.1 405B](/models/llama-3-1-405b) - Score: 30.77
- [Llama 4 Scout](/models/llama-4-scout) - Score: 29.42
- [Llama 3 70B](/models/llama-3-70b) - Score: 23.58
- [Llama 4 Maverick](/models/llama-4-maverick) - Score: 22.96
- [Muse Spark 1.3](/models/muse-spark-1-3) - Score: not computed
- [Llama 4 Behemoth](/models/llama-4-behemoth) - Score: not computed
- [Muse Voice Transcribe](/models/muse-voice-transcribe) - Score: not computed