CompliBench - Healthcare: leaderboard
Metric: Conversation-level accuracy (%): share of healthcare conversations in which the judge predicts both the governing guideline and the violation label correctly at every assistant turn, of an LLM judge on CompliBench's synthesized multi-turn dialogues with injected, adversarially optimized guideline violations, mean of four runs at default reasoning effort; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 57.11 |
| 2 | DeepSeek V3.2 (Thinking) | 39.68 |
| 3 | Claude Sonnet 4.6 | 39.41 |
| 4 | Qwen 3.5 Plus | 36.47 |
| 5 | GLM-5 | 33.26 |
| 6 | GPT-5 | 28.44 |
| 7 | Qwen 3 Max | 25.69 |
| 8 | Qwen 3 30B A3B | 25 |
| 9 | Kimi K2.5 | 22.94 |
| 10 | GPT-4o | 17.66 |
| 11 | Qwen 3 32B | 8.49 |
| 12 | Qwen 3 14B | 5.5 |
| 13 | Qwen 3 8B | 1.83 |
| 14 | Qwen 3 4B | 1.83 |
| 15 | GPT-4o Mini | 0.23 |
Interactive version: theaggregate.ai/benchmark?slug=complibench-healthcare · How It Works · Data refreshed daily, snapshot 2026-10-07.