AutoMedBench: leaderboard
48 medical-imaging tasks in 7 tracks (segmentation, VQA, report generation and more) that a coding agent must plan, run and submit; UC Santa Cruz and NVIDIA (2026); half rubric, half task metric.
Metric: Average Overall Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 69.69 |
| 2 | GLM-5 | 63.32 |
| 3 | Gemini 3.1 Pro (Preview) | 61.23 |
| 4 | MiniMax-M2.5 | 52.34 |
| 5 | Kimi K2.5 | 33.86 |
Interactive version: theaggregate.ai/benchmark?slug=automedbench · How It Works · Data refreshed daily, snapshot 2026-09-05.