List your company

Deep Search on BrowseComp-ZH (test)

58.1AccuracyOpenAI-o3
8.1821.1434.147.06Jan 9, 2026

Evaluation results

MethodLinks
OpenAI-o3Context Budget=128k2026.0158.1
GLM-4.6Context Budget=128k2026.0149.5
DeepSeek-v3.1Context Budget=128k2026.0149.2
Tongyi-DeepResearchContext Budget=128k2026.0146.7
GLM-4.5Context Budget=128k2026.0137.5
DeepDive-30B-SFT + C-GRPOContext Budget=128k2026.0133.3
WebExplorer-8BContext Budget=128k2026.0132
DeepDive-32BContext Budget=128k2026.0129.7
DeepDive-30B-SFT + GRPOContext Budget=128k2026.0126.1
DeepDive-30B-SFT + C-GRPOContext Budget=64k2026.0126
WebSailor-32BContext Budget=32k2026.0125.5
DeepDive-4B-SFT + C-GRPOContext Budget=128k2026.0124.7
DeepDive-30B-SFTContext Budget=128k2026.0124.7
DeepDive-30B-SFT + GRPOContext Budget=64k2026.0124.1
DeepDive-30B-SFT + E-GRPOContext Budget=128k2026.0124
DeepDive-4B-SFT + E-GRPOContext Budget=128k2026.0120.2
DeepDive-4B-SFT + C-GRPOContext Budget=64k2026.0118.2
DeepDive-4B-SFT + GRPOContext Budget=128k2026.0117.5
DeepDive-30B-SFT + E-GRPOContext Budget=64k2026.0117.1
DeepDive-4B-SFTContext Budget=128k2026.0116.6
DeepDive-4B-SFT + GRPOContext Budget=64k2026.0116.6
DeepDive-4B-SFT + E-GRPOContext Budget=64k2026.0116.5
DeepDive-30B-SFTContext Budget=64k2026.0115.8
Asearcher-Web-32BContext Budget=128k2026.0115.6
DeepDive-9BContext Budget=128k2026.0115.1
WebSailor-7BContext Budget=32k2026.0114.2
DeepDive-4B-SFTContext Budget=64k2026.0110.1