SurgCoT: leaderboard
Metric: Average over the five reasoning tasks of main-question accuracy (%) on SurgCoT surgical-video multiple-choice questions (2,841 videos across 7 specialties and 35 procedures), baseline setting with only the video and the main question, zero-shot, temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 76.62 |
| 2 | Claude Sonnet 4.5 | 74.1 |
| 3 | MedGemma-27B-IT | 70.96 |
| 4 | Gemini 2.5 Pro | 70.02 |
| 5 | Qwen 2.5 VL 7B | 68.85 |
Interactive version: theaggregate.ai/benchmark?slug=surgcot · How It Works · Data refreshed daily, snapshot 2026-10-07.