SurgiQ - Negative: leaderboard
Metric: Negative (all-except) questions (2,153): 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 | 68.31 |
| 2 | Qwen 2.5 72B Instruct | 68.03 |
| 3 | Qwen 2.5 32B Instruct | 67.01 |
| 4 | Ministral-3-14B-Reasoning-2512 | 64.96 |
| 5 | Qwen 2.5 32B | 64.82 |
| 6 | DeepSeek R1 Distill Qwen 32B | 64.36 |
| 7 | GPT-OSS-120B | 62.08 |
| 8 | DeepSeek R1 Distill Qwen 14B | 59.25 |
| 9 | GPT-OSS-20B | 48.98 |
| 10 | K2 Think V2 | 46.28 |
| 11 | Gemma 2 9B (IT) | 46.1 |
| 12 | Ministral-3-8B-Instruct-2512 | 43.12 |
| 13 | BioMistral-7B | 41.87 |
| 14 | MedGemma-27B-IT | 36.2 |
| 15 | DeepSeek-R1-Distill-Qwen-7B | 34.15 |
Interactive version: theaggregate.ai/benchmark?slug=surgiq-negative · How It Works · Data refreshed daily, snapshot 2026-09-29.