MedBench v5 - Medical Atomic Skills: leaderboard
The Medical Atomic Skills average of MedBench v5 (2026): the macro-average of four executable agent environments for clinical data analysis, retrieval-augmented answering, deep research and red-team safety, each scored 0-100. Higher is better.
Metric: Medical Atomic Skills average (0-100): macro-average of the DataAgent, RAGAgent, DeepResearch and SafetyAgent executable agent environment scores; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 81.22 | #49 |
| 2 | Kimi K2.6 | 74.49 | #178 |
| 3 | Seed 2.0 Pro | 74.1 | #211 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=medbench-v5-medical-atomic-skills · How It Works · Data refreshed daily, snapshot 2026-11-13.