SafePyramid - Exact Match: leaderboard
Metric: Rule matching rate (%) over all 3,000 SafePyramid cases: per case (a multi-turn conversation plus an in-context safety policy), the predicted set of violated rules matches the ground-truth set when neither false positives nor false negatives exceed (1 - tau) of the true violations; at tau = 1.0 only, i.e. the exact violated-rule set; per-policy evaluation, refused cases excluded; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 (Max) | 35 |
| 2 | GPT-5.5 (xHigh) | 34.9 |
| 3 | DeepSeek V4 Pro (Max) | 31.7 |
| 4 | Seed 2.0 Pro (High) | 29.5 |
| 5 | Qwen 3.6 Max (Preview) (Thinking) | 29.2 |
| 6 | Gemini 3.5 Flash (High) | 28.1 |
| 7 | Hy3-preview (High) | 27.4 |
| 8 | Grok 4.3 (High) | 25.1 |
| 9 | gpt-oss-safeguard-20B | 13.5 |
Interactive version: theaggregate.ai/benchmark?slug=safepyramid-exact-match · How It Works · Data refreshed daily, snapshot 2026-09-29.