Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

BPO

Benchmarks

Task NameDataset NameSOTA ResultTrend
Instruction FollowingBPO Eval (test)
A Wins59.5
19
Open-ended instruction followingBPO Eval (test)
Win Rate (A)59.5
7
Instruction Following EvaluationBPO Eval (test)
A Win Rate58.5
5
Showing 3 of 3 rows