MedPRMBench (Step Probability): leaderboard
Metric: PRMScore (%): mean of the F1 for erroneous steps and the F1 for correct steps (weights 0.5 and 0.5) in step-level error detection over the erroneous reasoning chains of the 6,500 MedPRMBench test instances (14 injected medical reasoning error types), step-probability protocol: at the delimiter after each step the model's probability of the plus token against the minus token is read, and a step is correct when that probability is at least 0.5; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Marco-o1 | 54.3 |
| 2 | QwQ-32B | 52.4 |
| 3 | DeepSeek R1 Distill Llama 70B | 51.1 |
| 4 | Qwen 3 8B | 51 |
| 5 | DeepSeek R1 Distill Qwen 32B | 49.7 |
Interactive version: theaggregate.ai/benchmark?slug=medprmbench-step-probability · How It Works · Data refreshed daily, snapshot 2026-10-07.