# Online Mind2Web 300 tasks on 136 live websites for evaluating web agents online, with outdated tasks replaced over time, human-reviewed submissions and the WebJudge automatic evaluator. - Catalog URL: https://awesomecua.github.io/resources/github-osu-nlp-group-online-mind2web/ - Original source: https://github.com/OSU-NLP-Group/Online-Mind2Web - Kind: benchmark - Review: curated - Scope: core - Environments: web - Topics: evaluation, web-navigation - Evidence checked: 2026-10-16T06:35:57Z - ID: github:osu-nlp-group/online-mind2web ## Limitations Inclusion does not establish reproducibility or endorsement. - Record JSON: https://awesomecua.github.io/resources/github-osu-nlp-group-online-mind2web/record.json ## Structured profile - actions: web interactions - evaluation: Human evaluation and WebJudge-based evaluation are documented as distinct assessment paths. - focus: live-web task completion - observations: not recorded - setting: interactive ### Count observations - 300 tasks — documented Online-Mind2Web suite (reported; source: https://raw.githubusercontent.com/OSU-NLP-Group/Online-Mind2Web/HEAD/README.md) - 136 websites — documented site coverage (reported; source: https://raw.githubusercontent.com/OSU-NLP-Group/Online-Mind2Web/HEAD/README.md) Tasks are actively replaced when websites or requirements become invalid. Record the task revision and submission schema; a constant headline task count does not imply an unchanged test set. ## License declarations - code: MIT — https://raw.githubusercontent.com/OSU-NLP-Group/Online-Mind2Web/HEAD/LICENSE - data: not recorded - document: not recorded - weights: not recorded ## Primary evidence - https://raw.githubusercontent.com/OSU-NLP-Group/Online-Mind2Web/HEAD/README.md (retrieved 2026-10-16T06:35:57Z; SHA-256 49d7cc317fd2ba0df65abf65a0357d1fa2384e59019a96d4e24b784888599eaa) - https://raw.githubusercontent.com/OSU-NLP-Group/Online-Mind2Web/HEAD/LICENSE (retrieved 2026-10-16T06:41:57Z; SHA-256 93675f9d13697ae98889d703b8fae86a7200623e7ae8d844c9ee2200ad480583)