AutoMedBench - Agentic Score (Standard): leaderboard
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 December 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 81.8 |
| 2 | GPT-5.4 | 78.9 |
| 3 | GLM-5 | 71.9 |
| 4 | Gemini 3.1 Pro (Preview) | 69.7 |
| 5 | MiniMax-M2.5 | 65.3 |
| 6 | Qwen 3.5 397B A17B | 61.7 |
Interactive version: theaggregate.ai/benchmark?slug=automedbench-agentic-score-standard · How It Works · Data refreshed daily, snapshot 2026-09-29.