LITMUS: leaderboard
Metric: Attack Success Rate (self-reported). Source: benchmarklist.com. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 40.64 |
| 2 | Qwen 3.6 Plus | 55.84 |
| 3 | Gemini 3.1 Pro (Preview) | 57.02 |
| 4 | GPT-5.3 Codex | 58.12 |
| 5 | DeepSeek V4 Pro | 69.8 |
| 6 | DeepSeek V3.2 | 71.51 |
Interactive version: theaggregate.ai/benchmark?slug=litmus · How It Works · Data refreshed daily, snapshot 2026-09-05.