MMedBench - Rationale (BLEU-1) — leaderboard
Metric: Accuracy (%). Source: henrychur.github.io. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-3.5 | 26.01 |
| 2 | Gemini 1.0 Pro | 7.28 |
Interactive version: theaggregate.ai/benchmark?slug=mmedbench-rationale-bleu-1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.