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

ScholarQA, HealthBench, ResearchQA, DeepResearchBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Open-ended deep researchScholarQA, HealthBench, ResearchQA, DeepResearchBench 200-question v2
ResearchQA Accuracy80.2
9
Showing 1 of 1 rows