General
Mind2Web candidate generation
Recorded candidate-generation rankings from the Mind2Web authors' fine-tuned DeBERTa-v3-base cross-encoder, joined to complete released train and test action-step inputs.
17,153items
1subjects
cc-by-4.0license
gui_agentdomain
tool_usedomain
textmodality
item-level responses released
Saturation status: No
Response matrix
Loading response matrix…
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect