DocAttriBench - MMLongBench-Doc: leaderboard

Metric: Overall answer correctness (%; grounded answer generation on MMLongBench-Doc (276 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 February 2028. 16 models tracked.

Top models

#ModelScore
1Qwen 2.5 VL 32B Instruct11.8
2Qwen 3 VL 8B7.7
3InternVL3-38B4.4
4Qwen 2.5 VL 7B Instruct3.7
5InternVL3-8B1.8
6InternVL2.5-2B0

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