Organization collection

userbench

Datasets published by this organization.

Organization inventory

DatasetAccessTasks
userbench/UserBench

UserBench eval: 620 next-message tasks across 62 developers. Composer 2.5 classifies gold and predicted messages into multi-label acts; reward is set Jaccard/IoU.

Public
620
userbench/UserBench-train400

UserBench train400 twin: the same 620 held tasks plus 400 leak-safe prior turns per developer. Composer 2.5 multi-label acts score by set Jaccard/IoU.

Public
620

2 datasets