List your company

Web Navigation Task Completion on Mind2Web Cross-task

64.6Success RatePolySkill (+Update)
51.80855.12958.4561.771Oct 17, 2025

Evaluation results

MethodLinks
PolySkill (+Update)Backbone=Claude-3.7-Sonnet, Training Tasks=1009 tasks2025.1064.6
PolySkill (+Update)Backbone=GPT-4.1, Training Tasks=1009 tasks2025.1063.2
PolySkill (Same sub-dom.)Backbone=Claude-3.7-Sonnet, Training Tasks=1009 tasks2025.1062.3
ASI (+Update)Backbone=Claude-3.7-Sonnet, Training Tasks=1009 tasks2025.1062.1
PolySkill (Same domain)Backbone=Claude-3.7-Sonnet, Training Tasks=1009 tasks2025.1062
PolySkill (All Skills)Backbone=Claude-3.7-Sonnet, Training Tasks=1009 tasks2025.1061.3
ASI (Same sub-domain)Backbone=Claude-3.7-Sonnet, Training Tasks=1009 tasks2025.1061.2
ASI (Same domain)Backbone=Claude-3.7-Sonnet, Training Tasks=1009 tasks2025.1060.9
ASI (All skills)Backbone=Claude-3.7-Sonnet, Training Tasks=1009 tasks2025.1060.3
ASI (+Update)Backbone=GPT-4.1, Training Tasks=1009 tasks2025.1059.4
BaselineBackbone=Claude-3.7-Sonnet, Training Tasks=1009 tasks2025.1059.1
PolySkill (Same sub-dom.)Backbone=GPT-4.1, Training Tasks=1009 tasks2025.1058.6
PolySkill (Same domain)Backbone=GPT-4.1, Training Tasks=1009 tasks2025.1058.3
ASI (Same sub-domain)Backbone=GPT-4.1, Training Tasks=1009 tasks2025.1056.3
PolySkill (All Skills)Backbone=GPT-4.1, Training Tasks=1009 tasks2025.1055.4
ASI (Same domain)Backbone=GPT-4.1, Training Tasks=1009 tasks2025.1055.2
BaselineBackbone=GPT-4.1, Training Tasks=1009 tasks2025.1053.8
ASI (All skills)Backbone=GPT-4.1, Training Tasks=1009 tasks2025.1052.3