MedProbeBench - Evidence Verification: 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. Evidence verification combining claim recall, search effectiveness (60% reference recall and 40% capped reference quantity), and factual consistency of cited claims, times 100; higher is better.
Metric: Evidence verification (x100): task-weighted composite of claim recall, search effectiveness (60% reference recall plus 40% capped reference quantity) and factual consistency of cited claims, 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 September 2027. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Baichuan-M2-Plus | 46.3 | |
| 2 | GPT-5.2 | 43.7 | #185 |
| 3 | Baichuan-M3-Plus | 42.7 | |
| 4 | Grok 4 | 41.4 | #319 |
| 5 | Gemini 3 Flash (Preview) | 40.1 | #152 |
| 6 | GPT-5 | 37.4 | #178 |
| 7 | GPT-4.1 | 35.6 | #505 |
| 8 | Claude Sonnet 4 | 33.6 | #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-evidence-verification · How It Works · Data refreshed daily, snapshot 2026-11-21.