CPGBench: leaderboard
Metric: Average (%) of the content detection, title grounding and adherence rates on CPGBench's 32,155 recommendations extracted from 3,418 clinical practice guidelines (nine regions, 24 specialties), each embedded in a synthetic multi-turn clinician-patient conversation, scored by a GPT-4o judge against the source recommendation; higher is better. Source: arxiv.org. Saturation forecast: Around April 2028. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 57.44 | #91 |
| 2 | Qwen 3 32B | 46.21 | #424 |
| 3 | GPT-4o | 44.1 | #333 |
| 4 | Qwen 3 4B 2507 Instruct | 37.83 | #745 |
| 5 | Llama 3 8B Instruct | 35.49 | #1115 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=cpgbench · How It Works · Data refreshed daily, snapshot 2026-10-11.