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

#ModelScoreOverall rank
1GPT-578.97#185
2MedGemma-27B-IT73.39#1359
3HuatuoGPT-Vision-7B67.24#2178
4LLaVA-Med-7B62.29#6340
5Qwen 2.5 VL 7B60.95#1878
6Qwen 3 VL 8B60.67#927
7Gemini 2.5 Pro60.31#280
8Claude Sonnet 4.559.8#267
9InternVL3.5-8B59.12#1618
10Lingshu-7B49.06#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.