Agents & tool use

Mind2Web

by The Ohio State University

What is Mind2Web? Mind2Web is an agents & tool use eval made by The Ohio State University. 2,350 tasks written for 137 real websites across 31 domains, such as booking flights or finding receipts, used to check whether a web agent can follow a plain-language instruction on sites it has not seen before.

Page last updated 2026-10-18 · Evals Review

Editor note

2,350 tasks written for 137 real websites across 31 domains, such as booking flights or finding receipts, used to check whether a web agent can follow a plain-language instruction on sites it has not seen before.

What it tests
Generalist web agents completing multi-step tasks across unseen sites and domains.
Original source
osu-nlp-group.github.io/Mind2Web/
Last updated
Repo last commit 2025-11-05
License
MIT

Facts come only from the linked source (checked 15–16 Oct 2026). Credit belongs to the creators. We don't score or rank evals: how we review.

Reviews

No reviews yet.

Reviews are written by people who sign in with GitHub, one per account per eval. We can't confirm that each reviewer used the eval; we remove reviews that break our rules, never just for being negative, and we never add, buy or edit reviews. Averages, when shown, come only from these reviews.

Reviews from practitioners who sign in with GitHub open soon.

Related agents & tool use evals

  • GAIA — General assistant skills: browsing, file handling, multi-step reasoning.
  • WebArena — Autonomous web navigation and task completion.
  • OSWorld — Computer-use agents operating real operating systems and apps.
  • Terminal-Bench — Agents working in the shell end to end.

All Agents & tool use evals · Comparison table