Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Meetings

Benchmarks

Task NameDataset NameSOTA ResultTrend
Step-level correctness assessmentMeetings (test)
PR-AUC81.9
22
Step-level reasoning verificationMeetings
PR-AUC73.4
19
MEP-Lobby link discoveryMeetings
AUC78
14
Showing 3 of 3 rows