SurgiQ - Orthopedic Surgery: leaderboard

Metric: Orthopedic surgery questions (1,189): 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 September 2027. 35 models tracked.

Top models

#ModelScore
1Qwen 2.5 72B62.99
2Qwen 2.5 72B Instruct62.32
3GPT-OSS-120B59.8
4Qwen 2.5 32B59.46
5Qwen 2.5 32B Instruct59.13
6Ministral-3-14B-Reasoning-251258.28
7DeepSeek R1 Distill Qwen 32B55.26
8GPT-OSS-20B51.89
9Ministral-3-8B-Instruct-251251.89
10DeepSeek R1 Distill Qwen 14B51.64
11K2 Think V249.96
12BioMistral-7B43.82
13Gemma 2 9B (IT)43.57
14MedGemma-4B-IT42.3
15MedGemma-27B-IT37.76

Interactive version: theaggregate.ai/benchmark?slug=surgiq-orthopedic-surgery · How It Works · Data refreshed daily, snapshot 2026-09-29.