WebSRC
Models answer questions about a web page from its screenshot, HTML or both. The set has 400K question and answer pairs from 6.4K web pages. Scored by exact match and F1.
Vision-language model reports use the dev split with screenshots only. Microsoft's Mage-VL card reports WebSRC-val.
- Released
- January 2021
- Kind
- Documents, charts and text in images
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
In the authors’ words
Web search is an essential way for humans to obtain information, but it's still a great challenge for machines to understand the contents of web pages. In this paper, we introduce the task of structural reading comprehension (SRC) on web. Given a web page and a question about it, the task is to find the answer from the web page. This task requires a system not only to understand the semantics of texts but also the structure of the web page. Moreover, we proposed WebSRC, a novel Web-based Structural Reading Comprehension dataset. WebSRC consists of 400K question-answer pairs, which are collected from 6.4K web pages. Along with the QA pairs, corresponding HTML source code, screenshots, and metadata are also provided in our dataset. Each question in WebSRC requires a certain structural understanding of a web page to answer, and the answer is either a text span on the web page or yes/no. We evaluate various baselines on our dataset to show the difficulty of our task. We also investigate the usefulness of structural information and visual features. Our dataset and baselines have been publicly available at https://x-lance.github.io/WebSRC/.
SageGPT-small-v0.2 tops the leaderboard with 89.1%
Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1 SageGPT-small-v0.2 89.1%
- 2 ScreenAI 5B 84%
- 3 DocPrompt (ErnieLayout-Large) 77.3%
- 4 TIE (MarkupLM-Large) 76.3%
- 5 MarkupLM-Large 69.9%
- 6 V-PLM (ELECTRA) 68.1%
- 7 V-PLM (BERT) 54.8%
Source: Official WebSRC leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | SageGPT-small-v0.2 | 89.1% | Official leaderboard | ||
| 2 | ScreenAI 5B | 84% | Official leaderboard | ||
| 3 | DocPrompt (ErnieLayout-Large) | 77.3% | Official leaderboard | ||
| 4 | TIE (MarkupLM-Large) | 76.3% | Official leaderboard | ||
| 5 | MarkupLM-Large | 69.9% | Official leaderboard | ||
| 6 | V-PLM (ELECTRA) | 68.1% | Official leaderboard | ||
| 7 | V-PLM (BERT) | 54.8% | Official leaderboard |
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7% - MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%
- ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9%