MedStruct-S (Two-Shot) - Key Discovery: leaderboard
Metric: Key F1 (%; exact key match, micro-averaged, OCR-derived Chinese clinical report pages, two-shot prompting, greedy decoding). Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 32B Instruct | 56.14 |
| 2 | Qwen 3 14B | 48.65 |
| 3 | Qwen 3 0.6B | 6.84 |
Interactive version: theaggregate.ai/benchmark?slug=medstruct-s-two-shot-key-discovery · How It Works · Data refreshed daily, snapshot 2026-09-26.