Published collection
OpenRouter uses BrowseComp to evaluate search configurations
Agent developers can use this to weigh search depth, model choice, and cost configuration.
- Published entries
- 1
- Sources
- 1
- Date range
- 2026-08-13
- Primary labels
- Workflows · 技巧 · Agent workflows · OpenRouter 实时网页搜索基准测试
Published evidence
Every entry keeps its summary and a path back to the source context.
OpenRouter uses BrowseComp to evaluate search configurations
OpenRouter releases a real-time leaderboard evaluating combinations of models, search engines, search methods, and budgets; results say increasing the search budget from 1 round to 25 rounds can nearly double BrowseComp scores, and model choice matters more than the search engine.
Original source