CompliBench - Healthcare: leaderboard
CompliBench (2026) evaluates LLMs as judges of guideline compliance in task-oriented dialogue: synthesized multi-turn conversations carry injected, adversarially optimized violations, and the judge must name the governing guideline and violation status of every assistant turn. This board is conversation-level accuracy in percent in the healthcare domain, the share of conversations judged correctly at every turn, averaged over four runs; higher is better.
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 February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Pro | 57.11 | #146 | |
| 2 | DeepSeek V3.2 | Thinking | 39.68 | #425 |
| 3 | Claude Sonnet 4.6 | 39.41 | #179 | |
| 4 | Qwen 3.5 Plus | 36.47 | #250 | |
| 5 | GLM-5 | 33.26 | #276 | |
| 6 | GPT-5 | 28.44 | #185 | |
| 7 | Qwen 3 Max | 25.69 | #420 | |
| 8 | Qwen 3 30B A3B | 25 | #1165 | |
| 9 | Kimi K2.5 | 22.94 | #272 | |
| 10 | GPT-4o | 17.66 | #754 | |
| 11 | Qwen 3 32B | 8.49 | #983 | |
| 12 | Qwen 3 14B | 5.5 | #1284 | |
| 13 | Qwen 3 8B | 1.83 | #1890 | |
| 14 | Qwen 3 4B | 1.83 | #2379 | |
| 15 | GPT-4o Mini | 0.23 | #1680 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=complibench-healthcare · How It Works · Data refreshed daily, snapshot 2026-11-22.