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

BizBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Open-Ended Professional TasksBizBench 1.0 (Leaderboard)
Final Score57.1
18
Financial Question AnsweringBizBench SEC-NUM
Accuracy79.3
9
Showing 2 of 2 rows