MedProbeBench: leaderboard

Expert-level medical guideline writing by LLMs with search tools on MedProbeBench (2026): each system writes a complete clinical guideline for 50 tumor entities from WHO classification volumes, compared with the expert guideline. Overall score combining holistic quality and claim-level evidence verification, times 100; higher is better.

Metric: Overall score (x100): task-weighted composite of holistic quality and fine-grained evidence verification, for LLMs with search tools on MedProbeBench: each system writes a complete clinical guideline for 50 WHO-classification tumor entities (one run per task), compared with the expert guideline; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Baichuan-M2-Plus52.9
2GPT-5.252.7#185
3Baichuan-M3-Plus49.8
4Grok 448.6#319
5Gemini 3 Flash (Preview)48.4#152
6GPT-547.2#178
7GPT-4.144.5#505
8Claude Sonnet 442.7#410

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=medprobebench · How It Works · Data refreshed daily, snapshot 2026-11-21.