RuleSafe-VL - Atomic Rule Identification: leaderboard
Metric: Macro-F1 (%; whether each candidate atomic policy rule is satisfied by an image-text case, mean of three policy families). Source: arxiv.org. Saturation forecast: Around 2028. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 69.3 |
| 2 | Gemini 3.1 Pro (Preview) | 68.8 |
| 3 | Qwen 3 VL 8B | 63 |
| 4 | Qwen 3 VL 4B | 59.8 |
| 5 | GPT-5.4 | 56.8 |
| 6 | Qwen 2.5 VL 7B Instruct | 47 |
Interactive version: theaggregate.ai/benchmark?slug=rulesafe-vl-atomic-rule-identification · How It Works · Data refreshed daily, snapshot 2026-09-25.