ClawsBench - Safety (Gemini CLI; skills on; meta on): leaderboard
Metric: Mean native task score x100 (-100 to 100); Gemini CLI, domain skills on, meta prompt on; mean over observed scored trials, including scored error rows; higher is better. Source: huggingface.co. 1 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | gemini-3.1-flash-lite-preview | -5 |
Interactive version: theaggregate.ai/benchmark?slug=clawsbench-safety-gemini-cli-skills-on-meta-on · How It Works · Data refreshed daily, snapshot 2026-10-09.