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

D_point

Benchmarks

Task NameDataset NameSOTA ResultTrend
Ternary Research Idea ClassificationD_point
Accuracy (3 Class)73.73
7
Binary Research Idea ClassificationD_point NeurIPS25 and ICLR25
Acc275.58
7
Research Idea EvaluationD_point (randomly sampled 60 instances)
Rationality Win Rate0.8848
5
Showing 3 of 3 rows