Model profile
Muse Glimmer
Evidence summary
Safety. Muse Glimmer has an estimated Safety rank of #268; its 90% source-sensitivity interval is #144–#305. Its behavior-only rank is #280; company governance moves the combined estimate to #268. Published Safety evidence spans 3 eval lineages and 4 of 7 components. Its strongest relative result is SM-Bench (ambiguous_interpretation, #26 of 84); its weakest is TAC (base_welfare_rate, #84 of 84).
Freedom. Muse Glimmer has an estimated Freedom rank of #237; its 90% source-sensitivity interval is #67–#627. Published Freedom evidence spans 3 eval lineages and 1 of 1 components. Its strongest relative result is SpeechMap model completion (complete_pct, #31 of 181); its weakest is SM-Bench (eq_boundaries, #70 of 84).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗muse-glimmer
- Hugging Face ↗meta-models/Muse-Glimmer-30B
- OpenRouter ↗meta/muse-glimmer-30b
- Official model page ↗Exact model document · Meta · first party
Finetunes
Direct finetunes linked to this canonical base model. Quantized and repackaged derivatives are excluded.
Blackfrost-AI/Muse-Glimmer-30B-Abliterated-BF16 ↗Direct non-quantized finetune documented by Hugging Face metadata- gjtgjt/Muse-Glimmer-30B-heretic-plus ↗Direct non-quantized finetune documented by Hugging Face metadata
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #179 / 338 | ↓0.8194 | Source ↗official | |
| SM-Benchadversarial | #45 / 84 | ↑81.46 | Source ↗official | |
| SM-Benchambiguous_interpretation | #26 / 84 | ↑88.99 | Source ↗official | |
| SM-Benchanti_hallucination | #39 / 84 | ↑94.5 | Source ↗official | |
| SM-Bencheq_boundaries | #70 / 84 | ↑53.93 | Source ↗official | |
| SM-Benchoverfit | #68 / 84 | ↑49.18 | Source ↗official | |
| TACbase_welfare_rate | #84 / 84 | ↑9.615 | Source ↗self run |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| SM-Benchadversarial | #38 / 84 | ↓81.46 | Source ↗official | |
| SM-Bencheq_boundaries | #70 / 84 | ↑53.93 | Source ↗official | |
| SM-Benchoverfit | #68 / 84 | ↑49.18 | Source ↗official | |
| SpeechMap model completioncomplete_pct | #31 / 181 | ↑80.1 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_adherence_score | #44 / 156 | ↑4.5 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_direct_score | #65 / 156 | ↑3.75 | Source ↗official |