WebQuest
Models answer questions from screenshots of one web page, several related pages, or a navigation trace. The test checks extraction and combination of information across pages.
Labs report the single-screen and multi-screen splits separately. The org is inferred from the author list, so check it.
In the authors’ words
The rise of powerful multimodal LLMs has enhanced the viability of building web agents which can, with increasing levels of autonomy, assist users to retrieve information and complete tasks on various human-computer interfaces. It is hence necessary to build challenging benchmarks that span a wide-variety of use cases reflecting real-world usage. In this work, we present WebQuest, a multi-page question-answering dataset that requires reasoning across multiple related web pages. In contrast to existing UI benchmarks that focus on multi-step web navigation and task completion, our dataset evaluates information extraction, multimodal retrieval and composition of information from many web pages. WebQuest includes three question categories: single-screen QA, multi-screen QA, and QA based on navigation traces. We evaluate leading proprietary multimodal models like GPT-4V, Gemini Flash, Claude 3, and open source models like InstructBLIP, PaliGemma on our dataset, revealing a significant gap between single-screen and multi-screen reasoning. Finally, we investigate inference time techniques like Chain-of-Thought prompting to improve model capabilities on multi-screen reasoning.
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Short answer A number, word or short string matched to a key.
GLM-4.6V leads with 69.3% among models released by Dec 2025
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Dec 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 GLM-4.6V 69.3%
- 2 GLM-4.5V 68.8%
- 3 GLM-4.1V-9B-Thinking 63.4%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GLM-4.6V | 69.3% | Dec 2025 | Model card | |
| 2 | GLM-4.5V | 68.8% | Aug 2025 | Model card | |
| 3 | GLM-4.1V-9B-Thinking | 63.4% | Jul 2025 | Model card |
3 models have held number one since its release in Sep 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs headline it less often now, last in Dec 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 8 Dec 2025 | GLM-4.6V | 69.3 | Mean of Webquest-SingleQA 79.5 / Webquest-MultiQA 59.0 |
| 11 Aug 2025 | GLM-4.5V | 68.8 | Mean of Webquest-SingleQA 76.9 / Webquest-MultiQA 60.6 |
| 1 Jul 2025 | GLM-4.1V-9B-Thinking | 63.4 | Mean of Webquest-SingleQA 72.1 / Webquest-MultiQA 54.7 |
3 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 1 Jan 2026 | GLM-4.6V technical report | Webquest-SingleQA 79.5, Webquest-MultiQA 59.0, GLM-4.6V thinking, no overall score (Table 2) | Capabilities | |
| 13 Aug 2025 | GLM-4.5V technical report | Webquest-SingleQA 76.9, Webquest-MultiQA 60.6, GLM-4.5V thinking, no overall score (Table 2) | Capabilities | |
| 1 Jul 2025 | GLM-4.1V-9B-Thinking technical report | Webquest-SingleQA 72.1, Webquest-MultiQA 54.7, GLM-4.1V-9B-Thinking thinking, no overall score (Table 2) | Capabilities |
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. Kimi K3.1 Pro 84.1%
- 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% - 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% - DocVQA In use Models answer 50,000 questions about 12,000 scanned document images by reading their text and layout. Scoring is ANLS, a string similarity to reference answers.
Seed1.5-VL 96.9%