List your company

Web Research on Xbench DeepSearch

64.6Pass@1Claude-4-Sonnet
3.03219.0163550.984Dec 2, 2025Dec 6, 2025Dec 10, 2025Dec 15, 2025Dec 19, 2025Dec 23, 2025Dec 28, 2025

Evaluation results

MethodLinks
Claude-4-Sonnet2025.1264.6
THINKMERGEmodel=WebSailor-32B, N=82025.1257.6
THINKMERGEmodel=WebSailor-32B, N=42025.1255.2
WebSailor-32Bvariant=Baseline2025.1250.4
THINKMERGEmodel=WebSailor-32B, N=22025.1250.2
THINKMERGEmodel=WebSailor-7B, N=42025.1248
THINKMERGEmodel=WebSailor-7B, N=82025.1247.2
THINKMERGEmodel=WebSailor-7B, N=22025.1243.2
ASearcher-Web-QwQparameters=32B2025.1242.1
WebSailor-7Bvariant=Baseline2025.1237.8
FoldAct-7Bp_drop=0, parameters=7B2025.1235.4
WebSailor-7Bparameters=7B2025.1234.3
FoldAct-7Bp_drop=0.5, parameters=7B2025.1232.9
THINKMERGEmodel=WebSailor-3B, N=22025.1226.8
WebSailor-3Bvariant=Baseline2025.1226.4
GPT-4.1-mini2025.1225.4
THINKMERGEmodel=WebSailor-3B, N=42025.1212.2
THINKMERGEmodel=WebSailor-3B, N=82025.125.4