List your company

Web Browsing Research on BrowseComp (BC)

67.8Pass@3Claude Opus 4.5
13.9827.952541.92555.8975Mar 7, 2026Mar 19, 2026Apr 1, 2026Apr 14, 2026Apr 26, 2026May 9, 2026May 22, 2026

Evaluation results

MethodLinks
Claude Opus 4.5Model Category=Frontier Proprietary Agents2026.0567.8
Quest-35BModel Category=Open-Weight Agents, Parameters=35B, Evaluation Strategy=discard-all strategy2026.0564.6
GPT-5Model Category=Frontier Proprietary Agents2026.0559.9
Gemini 3 ProModel Category=Frontier Proprietary Agents2026.0559.2
OpenAI-DRModel Category=Frontier Proprietary Agents2026.0551.5
Quest-35BModel Category=Open-Weight Agents, Parameters=35B2026.0545.5
Tongyi-DRModel Category=Open-Weight Agents2026.0543.4
Quest-30BModel Category=Open-Weight Agents, Parameters=30B2026.0537
WeDASModel=Miro-30B2026.0335
MiroFlowModel=Miro-30B2026.0333
WeDASModel=GPT-5-MINI2026.0330
MiroFlowModel=GPT-5-MINI2026.0329
OpenResearcherModel Category=Open-Weight Agents2026.0526.3
WebSailorModel=WebSailor-72B2026.0318.96
WebSailorModel=WebSailor-32B2026.0316.05