AutoMedBench - Lesion Detection: leaderboard
Metric: Overall run score (0-100) on the lesion detection track (4 detection tasks): the mean of the held-out task score (mAP at IoU 0.5, scaled to 0-100) and the workflow agentic score (Plan, Setup, Validate, Inference and Submit stages weighted 25/15/35/15/10, LLM judge for the first three); each model is the single agent of the benchmark harness (shared code-execution interface, system prompt, tool schema and default decoding; no vendor agent framework), runs averaged over the Lite and Standard tiers; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 85.7 |
| 2 | GLM-5 | 83.3 |
| 3 | Qwen 3.5 397B A17B | 81.4 |
| 4 | MiniMax-M2.5 | 80 |
| 5 | Gemini 3.1 Pro (Preview) | 77.2 |
| 6 | GPT-5.4 | 73.8 |
Interactive version: theaggregate.ai/benchmark?slug=automedbench-lesion-detection · How It Works · Data refreshed daily, snapshot 2026-09-29.