List your company

Report Generation on DeepResearch Gym (test)

70.4ClarityPrompt
29.42440.06250.761.338Jun 18, 2026

Evaluation results

MethodLinks
PromptParadigm=Naive, Backbone=Qwen3-32B2026.0670.469.181.176.7053.258.42
RAGParadigm=Naive, Backbone=Qwen3-32B2026.0664.667.274.6714.352.455.68
SCAFFOLDAGENTParadigm=Multi-Agent, Backbone=Qwen3-32B2026.0663.382.475.585.279.868.875.83
IRCoTParadigm=Single-Agent, Backbone=Qwen3-32B2026.0662.373.174.677.383.856.671.28
WebWeaverParadigm=Multi-Agent, Backbone=Qwen3-32B2026.0662.177.971.280.559.567.169.72
StackPlannerParadigm=Multi-Agent, Backbone=Qwen3-32B2026.0662.169.466.177.831.859.261.07
ReActParadigm=Single-Agent, Backbone=Qwen3-32B2026.0660.583.460.374.961.965.467.73
EDRParadigm=Multi-Agent, Backbone=Qwen3-32B2026.0655.876.874.684.989.562.774.05
WebShaperParadigm=Single-Agent, Backbone=Qwen3-32B2026.0649.45954.275.226.859.754.05
STORMParadigm=Multi-Agent, Backbone=Qwen3-32B2026.0631546765.581.54657.5