MedS-Bench - Text Summarization: leaderboard
The Text Summarization subtask of MedS-Bench (arXiv) — summarizing clinical and medical text; BLEU-1 (0–100), the first component of the published BLEU/ROUGE pair. Published overview values are retained where detailed tables differ.
Metric: BLEU-1 (0-100). Source: henrychur.github.io. Saturation forecast: Around September 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.5 Sonnet (20240620) | 26.29 | #299 |
| 2 | GPT-4 | 24.46 | #438 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=meds-bench-text-summarization · How It Works · Data refreshed daily, snapshot 2026-10-20.