Muse Glimmer 30B (Low): benchmark results
Provider: Meta. Released 2026-08-09. Access: Open.
Aggregate Rating 1602 ± 12, rank #707 of 2167 rated models, from 66 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AMIGO (Threshold 0.8) | 11.5 | Verified Correct accuracy in percent on AMIGO's dress galler | 100 |
| Meta Glimmer Reasoning Report - CIMemories (coverage ↑) | 66.4 | Published Score (%) | 100 |
| Meta Glimmer Reasoning Report - TauBench (Airline) | 79 | Published Score (%) | 100 |
| Medmarks - M-ARC | 80 | Score (%) | 96 |
| Medmarks - MedConceptsQA Hard | 78.53 | Score (%) | 88.6 |
| Medmarks - MedConceptsQA Medium | 85.2 | Score (%) | 88.6 |
| Medmarks - Med-HALT Reasoning FCT | 88.31 | Score (%) | 87.5 |
| Medmarks - SCTpublic | 71.91 | Score (%) | 87.5 |
| Medmarks - PubHealthBench Reviewed | 89.52 | Score (%) | 80.7 |
| Medmarks - MMLU-Pro Health | 77.83 | Score (%) | 78.4 |
| Medmarks - MedConceptsQA Easy | 98.55 | Score (%) | 78.4 |
| Medmarks - LongHealth Task 1 | 89.33 | Score (%) | 77.3 |
Interactive version: theaggregate.ai/model?slug=muse-glimmer-30b-low · How It Works · Data refreshed daily, snapshot 2026-10-22.