AutoMedBench - Agentic Score (Standard): leaderboard
The workflow score of AutoMedBench (2026), an end-to-end medical-AI research benchmark for LLM agents, over all 24 tasks in the Standard tier, where the agent chooses the method and environment itself from a plan-only brief. Plan, setup, validate, inference and submit stages are weighted 25, 15, 35, 15 and 10, the first three judged by an LLM from saved artifacts and traces, on a 0 to 100 scale. Higher is better.
Metric: Agentic workflow score (0-100) over all 24 tasks in the Standard tier (plan-only guidance: the agent selects the method and environment itself): Plan, Setup, Validate, Inference and Submit stage scores weighted 25/15/35/15/10, the first three judged by an LLM from saved artifacts and traces; each model is the single agent of the shared harness with default decoding; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 81.8 | #102 |
| 2 | GPT-5.4 | 78.9 | #123 |
| 3 | GLM-5 | 71.9 | #260 |
| 4 | Gemini 3.1 Pro (Preview) | 69.7 | #94 |
| 5 | MiniMax-M2.5 | 65.3 | #582 |
| 6 | Qwen 3.5 397B A17B | 61.7 | #246 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=automedbench-agentic-score-standard · How It Works · Data refreshed daily, snapshot 2026-11-13.