MedRepBench - Explanation Acceptability: leaderboard
Metric: Acceptability rate (%; share of patient-facing explanations a DeepSeek-R1 judge scores 1 or 2 on a 0-2 scale for factuality, reasoning and clarity; VLM on the report image only). Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 4 Maverick | 60.78 |
| 2 | InternVL3-38B | 51.15 |
| 3 | InternVL3-8B | 48.24 |
| 4 | InternVL3-14B | 47 |
| 5 | Llama 4 Scout | 46.84 |
| 6 | Qwen 2.5 VL 7B | 26.21 |
Interactive version: theaggregate.ai/benchmark?slug=medrepbench-explanation-acceptability · How It Works · Data refreshed daily, snapshot 2026-09-26.