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

ProsQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
ReasoningProsQA
Acc100
26
Prospective ReasoningProsQA
BCA36.5
9
Logical reasoningProsQA (test)
Accuracy99.4
7
Logical ReasoningProsQA
Accuracy98.5
6
Propositional Logic ReasoningProsQA (val)
Accuracy93.37
4
Question AnsweringProsQA
Accuracy91.8
3
Logical ReasoningProsQA Enhanced
OA (%)97.8
1
Showing 7 of 7 rows