SurgCoT - Cue-Action Alignment: leaderboard
Aligning pre-action cues with micro-actions to pinpoint when and where an action begins in surgical videos of SurgCoT (2026), multiple-choice questions over 2,841 videos from seven specialties, answered zero-shot with only the video and the main question. Main-question accuracy in percent; higher is better.
Metric: Cue-action alignment 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 February 2027. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 83.66 | #261 |
| 2 | GPT-5 | 80.99 | #178 |
| 3 | Gemini 2.5 Pro | 77.97 | #276 |
| 4 | Qwen 3 VL 8B | 75.51 | #917 |
| 5 | MedGemma-27B-IT | 74.02 | #1350 |
| 6 | InternVL3.5-8B | 70.08 | #1604 |
| 7 | HuatuoGPT-Vision-7B | 68.28 | #2162 |
| 8 | LLaVA-Med-7B | 66.1 | #6296 |
| 9 | Lingshu-7B | 65.83 | #1635 |
| 10 | Qwen 2.5 VL 7B | 65.64 | #1862 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=surgcot-cue-action-alignment · How It Works · Data refreshed daily, snapshot 2026-11-21.