MedRepBench - Item Name Recall: leaderboard
Structured extraction from photographed, screenshotted and electronic Chinese laboratory reports, from the report image alone; MedRepBench (Shang et al., 2025). Recall in percent of the reference items' item names, with items matched by normalized name within a budget of as many items as the reference lists; higher is better.
Metric: Field-level recall (%; item name of each ground-truth lab item, matched by exact normalized item name within the model's top-K items, K = number of reference items; VLM on the report image only). Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 7B | 89.9 | #1796 |
| 2 | InternVL3-38B | 88.72 | #905 |
| 3 | InternVL3-14B | 88.7 | #1184 |
| 4 | Llama 4 Maverick | 88.51 | #1105 |
| 5 | InternVL3-8B | 88.21 | #1695 |
| 6 | Llama 4 Scout | 87.9 | #1787 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=medrepbench-item-name-recall · How It Works · Data refreshed daily, snapshot 2026-11-12.