MedProbeBench: leaderboard
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 September 2027. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 52.7 |
| 2 | Grok 4 | 48.6 |
| 3 | Gemini 3 Flash (Preview) | 48.4 |
| 4 | GPT-5 | 47.2 |
| 5 | GPT-4.1 | 44.5 |
| 6 | Claude Sonnet 4 | 42.7 |
| 7 | Claude Sonnet 4 (Thinking) | 39.6 |
Interactive version: theaggregate.ai/benchmark?slug=medprobebench · How It Works · Data refreshed daily, snapshot 2026-10-07.