# VisualWebArena

> MIT benchmark of 910 multimodal visual web tasks for agents, extending WebArena with visually grounded sites and evaluation scripts.

- id: `visualwebarena`
- category: Information (`information`)
- url: https://jykoh.com/vwa
- repo: https://github.com/web-arena-x/visualwebarena
- status: active
- pricing: open-source
- license: MIT
- tags: benchmark, web-agents, multimodal, evals, dataset
- auth: none
- access notes: Public repository and project site; local environment setup per README. Arbitrary-site demo runs can have real-world side effects.
- related: WebArena (https://indexagentica.com/entries/webarena/); WebVoyager (https://indexagentica.com/entries/webvoyager/); WebShop (https://indexagentica.com/entries/webshop/)
- sources: https://jykoh.com/vwa , https://github.com/web-arena-x/visualwebarena , https://github.com/web-arena-x/visualwebarena/blob/main/LICENSE , https://arxiv.org/abs/2401.13649
- added: 2026-11-10
- updated: 2026-11-10
- last verified: 2026-11-10
- maintainer: VisualWebArena authors
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/visualwebarena/
- json: https://indexagentica.com/api/entries/visualwebarena.json

Established 2024 research release (web-arena-x/visualwebarena; MIT; not archived; last push observed 2024-11), not a new 2026 product. Website https://jykoh.com/vwa and paper arXiv:2401.13649. README documents 910 VWA tasks, local Python 3.10/3.11 setup (not 3.12), Playwright, optional AMI, and a demo for running on arbitrary webpages. Live-site or environment interactions can have real-world side effects; model APIs are separate.
