List your company

Web Research on BrowseComp-ZH

29.1Pass@1Claude-4-Sonnet
1.71688.825915.93523.0441Dec 2, 2025Dec 6, 2025Dec 10, 2025Dec 15, 2025Dec 19, 2025Dec 23, 2025Dec 28, 2025

Evaluation results

MethodLinks
Claude-4-Sonnet2025.1229.1
THINKMERGEmodel=WebSailor-32B, N=42025.1228.37
THINKMERGEmodel=WebSailor-32B, N=82025.1227.34
THINKMERGEmodel=WebSailor-32B, N=22025.1226.3
THINKMERGEmodel=WebSailor-7B, N=42025.1224.91
THINKMERGEmodel=WebSailor-7B, N=82025.1222.49
WebSailor-32Bvariant=Baseline2025.1221.97
THINKMERGEmodel=WebSailor-7B, N=22025.1221.45
ASearcher-Web-QwQparameters=32B2025.1215.6
FoldAct-7Bp_drop=0.5, parameters=7B2025.1215.2
FoldAct-7Bp_drop=0, parameters=7B2025.1214.3
WebSailor-7Bparameters=7B2025.1214.2
WebSailor-7Bvariant=Baseline2025.1214.01
MiroThinker-8B-DPO-v0.1parameters=8B2025.1213.6
THINKMERGEmodel=WebSailor-3B, N=22025.1211.76
WebSailor-3Bvariant=Baseline2025.128.67
GPT-4.1-mini2025.128.3
THINKMERGEmodel=WebSailor-3B, N=42025.124.15
THINKMERGEmodel=WebSailor-3B, N=82025.122.77