MedS-Bench - Text Classification: leaderboard
The Text Classification subtask of MedS-Bench (arXiv) — classifying clinical and medical documents; macro-F1 (%). Published overview values are retained where detailed tables differ.
Metric: Macro-F1 (%). Source: henrychur.github.io. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 | 68.06 | #438 |
| 2 | Claude 3.5 Sonnet (20240620) | 66.74 | #299 |
Interactive version: theaggregate.ai/benchmark?slug=meds-bench-text-classification · How It Works · Data refreshed daily, snapshot 2026-10-20.