DocAttriBench - VisualMRC: leaderboard

Metric: Overall answer correctness (%; grounded answer generation on VisualMRC (4,857 test questions): an answer counts only when its text matches the reference and its evidence box is correct; zero-shot, with model-specific prompts and box parsers; element-level evidence boxes from the MAPPET attribution pipeline over Docling layout regions, a box counting when IoU >= 0.5). Source: arxiv.org. Saturation forecast: Around September 2027. 16 models tracked.

Top models

#ModelScore
1Qwen 3 VL 8B14.3
2Qwen 2.5 VL 32B Instruct11.6
3InternVL3-8B4.2
4InternVL3-38B3.9
5Qwen 2.5 VL 7B Instruct2.7
6InternVL2.5-2B0.1

Interactive version: theaggregate.ai/benchmark?slug=docattribench-visualmrc · How It Works · Data refreshed daily, snapshot 2026-09-26.