IMCBench: leaderboard
Metric: Overall Score (1-5; mean of LLM-jury clinical safety, clinical accuracy and uncertainty handling). Source: arxiv.org. Saturation forecast: Around March 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 3.61 |
| 2 | Claude Sonnet 4.6 | 3.3 |
| 3 | GPT-5.2 | 3.29 |
| 4 | Claude Haiku 4.5 | 3.05 |
| 5 | Llama 4 Scout | 2.99 |
Interactive version: theaggregate.ai/benchmark?slug=imcbench · How It Works · Data refreshed daily, snapshot 2026-09-25.