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

NeurIPS

Benchmarks

Task NameDataset NameSOTA ResultTrend
Persona DiscriminationNeurIPS Cross-conference
Persona Separability (Δ)0.418
16
Scientific Idea GenerationNeurips 2025
Absolute Novelty Score4.28
12
Limitation GenerationNeurIPS OpenReview critiques (test)
CGT66.45
11
Review Score GenerationNeurIPS 2025
Avg Review Score4.8
10
Transductive Cognitive DiagnosisNeurIPS 20
AUC78.7
4
Cross-Domain Cognitive DiagnosisNeurIPS 20
AUC76.31
3
Inductive Cognitive DiagnosisNeurIPS 20
AUC76.59
3
Showing 7 of 7 rows