Meta Muse Glimmer 30B Card - CIMemories - Violation Rate: leaderboard
CIMemories: 2,500 synthetic scenarios testing whether models reveal sensitive user attributes in inappropriate contexts; violation rate, judged by Claude 4.6 Sonnet over 4 runs. Meta Muse Glimmer 30B model card (August 2026); the methodology report gives internal runs for all three models, Glimmer at high reasoning and Gemma 4 31B and Qwen3.6-27B in thinking mode; percent, lower is better.
Metric: Violation Rate (%, lower is better). Source: huggingface.co. Saturation forecast: Around February 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 4 31B (Reasoning) | 12.1 | #212 (Gemma 4 31B) |
| 2 | Muse Glimmer 30B (High) | 26.4 | #191 (Muse Glimmer 30B) |
| 3 | Qwen 3.6 27B (Reasoning) | 53.4 | #182 (Qwen 3.6 27B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=meta-muse-glimmer-30b-card-cimemories-violation-rate · How It Works · Data refreshed daily, snapshot 2026-11-05.