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

20 Questions

Benchmarks

Task NameDataset NameSOTA ResultTrend
Information gathering20 Questions Plants (test)
Success Rate22.8
6
Information gathering20 Questions Animals (test)
Success Rate39.2
6
Entity Deduction20 Questions
SR89.2
4
Showing 3 of 3 rows