MMedBench — leaderboard
Metric: Accuracy (%). Source: henrychur.github.io. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 | 74.27 |
| 2 | Mistral | 60.73 |
| 3 | GPT-3.5 | 51.82 |
Interactive version: aibenchmarks.dev/benchmark?slug=mmedbench · How the rankings work · Data refreshed daily, snapshot 2026-07-08.