Oncology Report-Derived VQA - Liver CT Report-Derived: leaderboard
Metric: Accuracy (%; zero-shot multiple-choice VQA with 2-5 options on one representative 2D slice of a 3D study, the model sees the image, question and options but never the report; invalid responses excluded; liver CT, 1,000 cases, 8,901 LLM-written questions checked against the report). Source: arxiv.org. Saturation forecast: Around 2029. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | MedGemma-27B-IT | 64.5 |
| 2 | Claude Opus 4.6 | 61.7 |
| 3 | GPT-5.2 | 44 |
| 4 | GPT-5 | 40.6 |
Interactive version: theaggregate.ai/benchmark?slug=oncology-report-derived-vqa-liver-ct-report-derived · How It Works · Data refreshed daily, snapshot 2026-09-26.