SurgiQ - Robotic Surgery: leaderboard
Metric: Robotic surgery questions (1,643): accuracy (%) on SurgiQ's four-option surgical multiple-choice questions, zero-shot; the answer is the option label with the highest next-token log-probability (plain and space-prefixed labels), options shuffled once. Source: arxiv.org. Saturation forecast: Around December 2026. 35 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 72B | 69.08 |
| 2 | Qwen 2.5 72B Instruct | 68.17 |
| 3 | Qwen 2.5 32B Instruct | 65.73 |
| 4 | Qwen 2.5 32B | 65.67 |
| 5 | Ministral-3-14B-Reasoning-2512 | 64.09 |
| 6 | GPT-OSS-120B | 62.75 |
| 7 | DeepSeek R1 Distill Qwen 32B | 61.84 |
| 8 | GPT-OSS-20B | 57.15 |
| 9 | Ministral-3-8B-Instruct-2512 | 56.79 |
| 10 | DeepSeek R1 Distill Qwen 14B | 56.66 |
| 11 | K2 Think V2 | 53.68 |
| 12 | BioMistral-7B | 48.87 |
| 13 | Gemma 2 9B (IT) | 46.93 |
| 14 | MedGemma-4B-IT | 45.71 |
| 15 | Gemma 2 2B (IT) | 37.01 |
Interactive version: theaggregate.ai/benchmark?slug=surgiq-robotic-surgery · How It Works · Data refreshed daily, snapshot 2026-09-29.