Enhancing Agent Safety Judgment — leaderboard
Metric: Original (Seed) (self-reported). Source: benchmarklist.com. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 93.68 |
| 2 | Claude 3.7 Sonnet | 90.59 |
| 3 | Qwen 3 235B A22B | 89.42 |
| 4 | DeepSeek V3 | 88.24 |
| 5 | Qwen 3 8B | 81.82 |
Interactive version: theaggregate.ai/benchmark?slug=enhancing-agent-safety-judgment · How the rankings work · Data refreshed daily, snapshot 2026-07-22.