List your company

Deep Search on BrowseComp (test)

49.7AccuracyOpenAI-o3
3.4215.43527.4539.465Jan 9, 2026

Evaluation results

MethodLinks
OpenAI-o3Context Budget=128k2026.0149.7
GLM-4.6Context Budget=128k2026.0145.1
Tongyi-DeepResearchContext Budget=128k2026.0143.4
DeepSeek-v3.1Context Budget=128k2026.0130
GLM-4.5Context Budget=128k2026.0126.4
DeepDive-30B-SFT + C-GRPOContext Budget=128k2026.0124.8
DeepDive-30B-SFTContext Budget=128k2026.0120.5
DeepDive-30B-SFT + GRPOContext Budget=128k2026.0118.9
DeepDive-30B-SFT + E-GRPOContext Budget=128k2026.0118.5
DeepDive-30B-SFT + C-GRPOContext Budget=64k2026.0117.9
DeepDive-4B-SFT + C-GRPOContext Budget=128k2026.0117.5
DeepDive-30B-SFT + GRPOContext Budget=64k2026.0116
DeepDive-32BContext Budget=128k2026.0115.3
WebExplorer-8BContext Budget=128k2026.0115.2
DeepDive-4B-SFT + GRPOContext Budget=128k2026.0114.7
DeepDive-4B-SFT + E-GRPOContext Budget=128k2026.0114.5
DeepDive-4B-SFTContext Budget=128k2026.0114.1
DeepDive-4B-SFT + C-GRPOContext Budget=64k2026.0113.9
DeepDive-30B-SFT + E-GRPOContext Budget=64k2026.0113.1
DeepDive-4B-SFT + GRPOContext Budget=64k2026.0112.9
DeepDive-30B-SFTContext Budget=64k2026.0112.2
DeepDive-4B-SFT + E-GRPOContext Budget=64k2026.0111.5
WebSailor-32BContext Budget=32k2026.0110.5
DeepDive-4B-SFTContext Budget=64k2026.017.7
WebSailor-7BContext Budget=32k2026.016.7
DeepDive-9BContext Budget=128k2026.016.3
Asearcher-Web-32BContext Budget=128k2026.015.2