Med-R2 - Joint QA: leaderboard
Metric: Accuracy (%) on the Med-R2 Joint QA task (answering all reasoning levels for one image in a single prompt), zero-shot with system prompts; each task mixes equal numbers of positive, negative and neutral adversarial question forms; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (Thinking) | 90.2 |
| 2 | Qwen 3 VL 235B A22B | 72.5 |
| 3 | GPT-4o | 65.5 |
| 4 | Qwen 2.5 VL 7B Instruct | 57.3 |
| 5 | MedGemma-4B | 45.3 |
Interactive version: theaggregate.ai/benchmark?slug=med-r2-joint-qa · How It Works · Data refreshed daily, snapshot 2026-10-07.