SurgCoT - Affordance Mapping: leaderboard
Grounding tool-tissue interactions in space and time 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: Affordance mapping 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 | GPT-5 | 78.97 | #185 |
| 2 | MedGemma-27B-IT | 73.39 | #1359 |
| 3 | HuatuoGPT-Vision-7B | 67.24 | #2178 |
| 4 | LLaVA-Med-7B | 62.29 | #6340 |
| 5 | Qwen 2.5 VL 7B | 60.95 | #1878 |
| 6 | Qwen 3 VL 8B | 60.67 | #927 |
| 7 | Gemini 2.5 Pro | 60.31 | #280 |
| 8 | Claude Sonnet 4.5 | 59.8 | #267 |
| 9 | InternVL3.5-8B | 59.12 | #1618 |
| 10 | Lingshu-7B | 49.06 | #1646 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=surgcot-affordance-mapping · How It Works · Data refreshed daily, snapshot 2026-11-22.