MedS-Bench - Text Classification — leaderboard
Metric: Score. Source: henrychur.github.io. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama3.1-Aloe-Beta-8B | 73.45 |
| 2 | GPT-4 | 68.06 |
| 3 | Claude 3.5 Sonnet (20240620) | 66.74 |
| 4 | Mistral | 48.73 |
Interactive version: aibenchmarks.dev/benchmark?slug=meds-bench-text-classification · How the rankings work · Data refreshed daily, snapshot 2026-07-08.