Mind2Web
Human demonstrations and tasks for generalist web navigation research.
AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.
What is this resource?
- Resource type
- Benchmarks
- Environment
- web
- Topics
- evaluation, web-navigation
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-16T06:35:57Z
- Resource ID
- github:osu-nlp-group/mind2web
What licenses are recorded?
Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.
- Code
- MIT (repository LICENSE header; not a weights/data license)
- Data
- Not recorded
- Document
- Not recorded
- Weights
- Not recorded
Evaluation protocol
- Focus
- web action prediction, generalization to unseen sites and domains
- Setting
- offline
- Observations
- task instructions, HTML, recorded action history
- Actions / outputs
- CLICK, TYPE, SELECT
- Evaluation
- Offline candidate and action evaluation against recorded demonstrations; the repository distinguishes macro from micro averaging.
Scale and counting units
- 1,009 task instances — train split source
- 252 task instances — cross-task test split source
- 177 task instances — cross-website test split source
- 912 task instances — cross-domain test split source
These are reported split inventories, not online task-success measurements. Original Mind2Web, Multimodal-Mind2Web, and Online-Mind2Web have different inputs/protocols. The authors require macro-average metrics for comparison with the paper; test archives remain upstream.
Compare source-reviewed profiles
Explore related topics
Related resources
- documented by: Mind2Web: Towards a Generalist Agent for the Web
Primary evidence and verification
Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.
- editorial primary review
Retrieved 2026-10-16T06:35:57Z. Supports: name, kind, summary, environments, topics, scope, relations, details.
Content fingerprint
157dbd840264ea29f958c0b7383d63783845c573b3e19a1f39b773be22e0b32d - editorial primary review
Retrieved 2026-10-16T06:35:57Z. Supports: details.benchmark_protocol.
Content fingerprint
157dbd840264ea29f958c0b7383d63783845c573b3e19a1f39b773be22e0b32d - license header
Retrieved 2026-10-16T06:41:57Z. Supports: licenses.code.
Content fingerprint
953ff47dbbc0c0563d1ec2d245b06d1206f2f38c4ed2f0da728e027ae2e5a973
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.