DocAttriBench - Answer Locating: leaderboard
Metric: Box F1 (%; answer locating: given only the question, predict the evidence boxes, mean over the seven test sets DocVQA, VisualMRC, VISA, SlideVQA, VisualWebBench, LongDocURL and MMLongBench-Doc; 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 December 2026. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 8B | 21.1 |
| 2 | Qwen 2.5 VL 32B Instruct | 19.3 |
| 3 | InternVL3-38B | 18.6 |
| 4 | Qwen 2.5 VL 7B Instruct | 17.9 |
| 5 | InternVL3-8B | 11.1 |
| 6 | InternVL2.5-2B | 0.4 |
Interactive version: theaggregate.ai/benchmark?slug=docattribench-answer-locating · How It Works · Data refreshed daily, snapshot 2026-09-26.