Muse Glimmer 30B (xHigh): benchmark results
Provider: Meta. Released 2026-08-09. Access: Open.
Aggregate Rating 1652 ± 17, rank #514 of 2168 rated models, from 100 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Medmarks - M-ARC | 86.67 | Score (%) | 99.4 |
| Medmarks - Med-HALT Reasoning FCT | 91.57 | Score (%) | 96.6 |
| Medmarks - Med-HALT Reasoning NOTA | 71.63 | Score (%) | 94.3 |
| Medmarks - MetaMedQA | 79.95 | Score (%) | 94.3 |
| Nejumi 4 - M-IFEval (Japanese) | 90.71 | Score (%) | 93.7 |
| Medmarks - MedConceptsQA Hard | 83.68 | Score (%) | 93.2 |
| Medmarks - MedConceptsQA Medium | 88.1 | Score (%) | 92 |
| Medmarks - MedConceptsQA Easy | 99.18 | Score (%) | 87.5 |
| Medmarks - MedCalc-Bench | 72 | Score (%) | 86.4 |
| UGI - Natural Intelligence | 37.13 | NatInt Score | 83.7 |
| Nejumi 4 - jaster (0-shot) - JaNLI | 100 | Exact match (%) | 82.9 |
| Medmarks - LongHealth Task 1 | 90.42 | Score (%) | 82.4 |
Interactive version: theaggregate.ai/model?slug=muse-glimmer-30b-xhigh · How It Works · Data refreshed daily, snapshot 2026-10-20.