List your company

Report Generation on DeepResearch Bench

48.27Overall ScoreSCAFFOLDAGENT
32.191636.365840.5444.7142Jun 18, 2026

Evaluation results

MethodLinks
SCAFFOLDAGENTBackbone=DeepSeek-V3.2, Paradigm=Multi-Agent2026.0648.2746.449.6748.9847.3151.1862.2
StackPlannerBackbone=DeepSeek-V3.2, Paradigm=Multi-Agent2026.0646.8246.4246.2948.2546.7532.7550.4
SCAFFOLDAGENTBackbone=Qwen3-32B, Paradigm=Multi-Agent2026.0644.743.5445.2546.4942.8530.4254.32
PromptBackbone=DeepSeek-V3.2, Paradigm=Naive2026.0643.6841.7741.6747.2146.35——
WebWeaverBackbone=DeepSeek-V3.2, Paradigm=Multi-Agent2026.0643.5241.2742.3747.1844.913988.35
ReActBackbone=DeepSeek-V3.2, Paradigm=Single-Agent2026.0643.2642.740.5346.146.434.1517.83
EDRBackbone=DeepSeek-V3.2, Paradigm=Multi-Agent2026.0643.1341.9540.2746.2444.524.2834.79
IRCoTBackbone=Qwen3-32B, Paradigm=Single-Agent2026.0642.4640.739.5546.2345.715.7740.04
ReActBackbone=Qwen3-32B, Paradigm=Single-Agent2026.0642.2140.6638.6546.144.564.6923.78
StackPlannerBackbone=Qwen3-32B, Paradigm=Multi-Agent2026.0641.5539.8437.7946.4144.799.6326.5
WebWeaverBackbone=Qwen3-32B, Paradigm=Multi-Agent2026.0641.2839.8839.6844.6539.698.4232.72
EDRBackbone=Qwen3-32B, Paradigm=Multi-Agent2026.0640.9939.4934.6145.2239.6518.7823.7
IRCoTBackbone=DeepSeek-V3.2, Paradigm=Single-Agent2026.0639.7336.836.8144.5740.734.8375.18
PromptBackbone=Qwen3-32B, Paradigm=Naive2026.0639.5436.8735.2545.3443.67——
RAGBackbone=DeepSeek-V3.2, Paradigm=Naive2026.0639.536.4637.1943.3542.835.5116.18
RAGBackbone=Qwen3-32B, Paradigm=Naive2026.0636.6834.4933.3543.0742.922.9310.86
STORMBackbone=DeepSeek-V3.2, Paradigm=Multi-Agent2026.0635.2633.6931.5239.0239.0717.4238.59
WebShaperBackbone=Qwen3-32B, Paradigm=Single-Agent2026.0634.9331.5826.1744.8140.38——
WebShaperBackbone=DeepSeek-V3.2, Paradigm=Single-Agent2026.0634.9331.5826.1744.8140.38——
STORMBackbone=Qwen3-32B, Paradigm=Multi-Agent2026.0632.8130.6331.6634.8836.915.1836.9