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

Open-ended Deep Research on Composite Suite (ScholarQA, HealthBench, ResearchQA, DeepResearchBench v2)

80.2ResearchQA Accuracy

SearchSwarm

55.13661.64368.1574.657Jun 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
80.279.252.844.464.2
2026.06
79.279.653.846.964.9
2026.06
75.788.352.845.465.6
2026.06
75.367.3-42.3-
2026.06
74.5-47.544.4-
2026.06
74.246.739.440.650.2
2026.06
66.746.546.240.650
2026.06
60.941.924.540.341.9
2026.06
56.140.416.533.336.6