DocAttriBench - LongDocURL: leaderboard

Metric: Overall answer correctness (%; grounded answer generation on LongDocURL (688 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 2028. 16 models tracked.

Top models

#ModelScore
1Qwen 3 VL 8B7
2Qwen 2.5 VL 32B Instruct5.8
3Qwen 2.5 VL 7B Instruct3.7
4InternVL3-38B2.2
5InternVL3-8B1.9
6InternVL2.5-2B0

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