MedProbeBench - Claim Recall: leaderboard
Metric: Task success rate (x100): share of the expert guideline atomic claims that the generated guideline covers (semantic matching, deduplicated), 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 2028. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 35.3 |
| 2 | Claude Sonnet 4 | 34.2 |
| 3 | GPT-5 | 34 |
| 4 | Gemini 3 Flash (Preview) | 31.9 |
| 5 | Claude Sonnet 4 (Thinking) | 31.8 |
| 6 | GPT-4.1 | 30.1 |
| 7 | Grok 4 | 29.6 |
Interactive version: theaggregate.ai/benchmark?slug=medprobebench-claim-recall · How It Works · Data refreshed daily, snapshot 2026-10-07.