List your company

Deep Search on Browsecomp

52AccuracyGLM-4.7
-1.35212.49926.3540.201Jan 26, 2026Feb 15, 2026Mar 7, 2026Mar 28, 2026Apr 17, 2026May 7, 2026May 28, 2026

Evaluation results

MethodLinks
GLM-4.7Context Budget=-2026.0552
OpenAI-o3Context Budget=-2026.0549.7
GLM-4.6Context Budget=-2026.0549.5
Qwen3-30B-A3B-thinking-SFT + SAPOContext Budget=128K2026.0542.8
Tongyi DeepResearchContext Budget=128K2026.0540.7
Qwen3-30B-A3B-thinking-SFT + GRPOContext Budget=128K2026.0514.9
Kimi K2Context Budget=-2026.0514.1
Qwen3-30B-A3B-thinking-SFTContext Budget=128K2026.0513.9
Web-30B-E-GRPOContext Budget=-2026.0512.9
WebSailor-32BContext Budget=32K2026.055.5
Qwen3-8B-SFT + SAPOContext Budget=64K2026.054.9
Qwen3-8B-SFT + GRPOContext Budget=64K2026.054.3
Qwen3-8B-SFT + ARPOContext Budget=64K2026.054.1
WebExplorer-8BContext Budget=64K2026.052.9
Qwen3-8B-SFTContext Budget=64K2026.052.7
SAGEBackbone=QWEN-7B, Training data=SAGE (Ours), Search Engine=Google Search, Max queries=202026.012.6
MiroThinker-v1.0-8BContext Budget=64K2026.052.2
MusiqueBackbone=QWEN-7B, Training data=Musique, Search Engine=Google Search, Max queries=202026.012.1
NQ + HotpotQABackbone=QWEN-7B, Training data=NQ + HotpotQA, Search Engine=Google Search, Max queries=202026.011.6
NQ + HotpotQABackbone=QWEN-3B, Training data=NQ + HotpotQA, Search Engine=Google Search, Max queries=202026.011
MusiqueBackbone=QWEN-3B, Training data=Musique, Search Engine=Google Search, Max queries=202026.011
SAGEBackbone=QWEN-3B, Training data=SAGE (Ours), Search Engine=Google Search, Max queries=202026.011
WebSailor-7BContext Budget=32K2026.051
MiroThinker-v1.5-30BContext Budget=128K2026.050.7