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

AI Idea Bench and LiveIdeaBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Scientific Proposal GenerationAI Idea Bench and LiveIdeaBench 24 held-out benchmark groups 2025
Novelty3.04
7
Showing 1 of 1 rows