List your company

Deep Search on GAIA text-only (val)

70.9AccuracyTongyi-DeepResearch
36.5845.4954.463.31Jan 9, 2026

Evaluation results

MethodLinks
Tongyi-DeepResearchContext Budget=128k2026.0170.9
OpenAI-o3Context Budget=128k2026.0170.5
GLM-4.5Context Budget=128k2026.0166
DeepSeek-v3.1Context Budget=128k2026.0163.1
DeepDive-30B-SFT + C-GRPOContext Budget=128k2026.0156.3
DeepDive-30B-SFT + E-GRPOContext Budget=128k2026.0155.3
DeepDive-30B-SFT + C-GRPOContext Budget=64k2026.0153.7
Asearcher-Web-32BContext Budget=128k2026.0152.8
DeepDive-30B-SFT + E-GRPOContext Budget=64k2026.0152.8
WebSailor-32BContext Budget=32k2026.0151.5
DeepDive-30B-SFT + GRPOContext Budget=64k2026.0151.1
DeepDive-30B-SFT + GRPOContext Budget=128k2026.0151.1
DeepDive-30B-SFTContext Budget=128k2026.0150.8
DeepDive-4B-SFT + C-GRPOContext Budget=128k2026.0150.2
WebExplorer-8BContext Budget=128k2026.0150
DeepDive-4B-SFT + C-GRPOContext Budget=64k2026.0148.9
DeepDive-4B-SFTContext Budget=128k2026.0146
DeepDive-30B-SFTContext Budget=64k2026.0146
DeepDive-4B-SFT + E-GRPOContext Budget=64k2026.0142.4
DeepDive-4B-SFT + E-GRPOContext Budget=128k2026.0142.4
DeepDive-4B-SFT + GRPOContext Budget=128k2026.0141.1
DeepDive-4B-SFT + GRPOContext Budget=64k2026.0140.5
DeepDive-4B-SFTContext Budget=64k2026.0139.5
WebSailor-7BContext Budget=32k2026.0137.9