DRBench (Dense-Scene Reasoning): leaderboard
Metric: Combined accuracy (%; question-count-weighted mean of multiple-choice letter accuracy and open-ended semantic accuracy judged by Qwen-Max; 959 test questions). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Phi-4 Multimodal Instruct | 45.8 |
| 2 | Qwen 2.5 VL 32B Instruct | 44.7 |
| 3 | InternVL2.5-2B | 32.5 |
Interactive version: theaggregate.ai/benchmark?slug=drbench-dense-scene-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-26.