MM-NeuroOnco (Open-Ended) - Detail: leaderboard
Metric: Judge score (% of the maximum) on detailed findings; open-ended answers on MM-NeuroOnco-Bench's 1,000 brain-tumor MRI slices, scored 0-10 by a Qwen3-80B-Instruct judge with a hierarchical rubric that caps answers with critical safety errors (for example laterality confusion), mean shown times 10; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.1 | 71.15 | #131 |
| 2 | Gemini 3 Flash | 65.71 | #93 |
| 3 | MedGemma 1.5 4B | 50.89 | #775 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=mm-neuroonco-open-ended-detail · How It Works · Data refreshed daily, snapshot 2026-10-11.