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 (imported). Source: github.com. Source: benchmarklist.com. Saturation forecast: Around June 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 69.69 | #63 |
| 2 | GLM-5 | 63.32 | #141 |
| 3 | Gemini 3.1 Pro (Preview) | 61.23 | #58 |
| 4 | MiniMax-M2.5 | 52.34 | #303 |
| 5 | Kimi K2.5 | 33.86 | #144 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=automedbench · How It Works · Data refreshed daily, snapshot 2026-10-20.