Web Browsing on BC-plus (EM, F1)
29.6EMLongCat-Flash-Summary
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LongCat-Flash-SummaryMethod Strategy=Summary, Backbone=LongCat-Flash2026.05 | 29.6 | 35.7 | |
| GPT-4o-ReActMethod Strategy=ReAct, Backbone=GPT-4o2026.05 | 25.2 | 31.6 | |
| LongCat-Flash-ReActMethod Strategy=ReAct, Backbone=LongCat-Flash2026.05 | 24.4 | 28.5 | |
| ZipRL-14BMethod Strategy=Specialized Agent, Backbone=Qwen3-14B2026.05 | 24.4 | 27 | |
| ZipRL-4BMethod Strategy=Specialized Agent, Backbone=Qwen3-4B2026.05 | 24 | 26.9 | |
| ZipRL-14BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-14B2026.05 | 23.6 | 26.1 | |
| Gemini-3-Pro-SummaryMethod Strategy=Summary, Backbone=Gemini-3-Pro2026.05 | 23.2 | 27.4 | |
| Gemini-3-Pro-ReActMethod Strategy=ReAct, Backbone=Gemini-3-Pro2026.05 | 22.8 | 27.8 | |
| ZipRL-3BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-3B2026.05 | 22.5 | 24.8 | |
| ZipRL-8BMethod Strategy=Specialized Agent, Backbone=Qwen3-8B2026.05 | 20.8 | 23 | |
| ZipRL-7BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-7B2026.05 | 19.5 | 21.5 | |
| GPT-4o-SummaryMethod Strategy=Summary, Backbone=GPT-4o2026.05 | 17.6 | 27.7 | |
| WebSailor-32BMethod Strategy=Standard, Backbone=WebSailor-32B2026.05 | 17.6 | 25.6 | |
| AgentFold-4BMethod Strategy=Specialized Agent, Backbone=Qwen3-4B2026.05 | 15.6 | 19.8 | |
| AgentFold-8BMethod Strategy=Specialized Agent, Backbone=Qwen3-8B2026.05 | 15.6 | 19.3 | |
| AgentFold-14BMethod Strategy=Specialized Agent, Backbone=Qwen3-14B2026.05 | 14.8 | 16.9 | |
| Qwen3-235B-ReActMethod Strategy=ReAct, Backbone=Qwen3-235B2026.05 | 14 | 19.5 | |
| Qwen3-235B-SummaryMethod Strategy=Summary, Backbone=Qwen3-235B2026.05 | 14 | 19.2 | |
| ASearcher-14BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-14B2026.05 | 13.2 | 17.9 | |
| NestBrowse-4BMethod Strategy=Specialized Agent, Backbone=Qwen3-4B2026.05 | 11.2 | 15.7 | |
| DeepSeek-V3.2-ReActMethod Strategy=ReAct, Backbone=DeepSeek-V3.22026.05 | 8.8 | 13.3 | |
| NestBrowse-8BMethod Strategy=Specialized Agent, Backbone=Qwen3-8B2026.05 | 8.8 | 14.5 | |
| DeepSeek-V3.2-SummaryMethod Strategy=Summary, Backbone=DeepSeek-V3.22026.05 | 7.6 | 11.5 | |
| NestBrowse-14BMethod Strategy=Specialized Agent, Backbone=Qwen3-14B2026.05 | 7.6 | 11.7 | |
| WebSailor-7BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-7B2026.05 | 6.4 | 8.3 | |
| ASearcher-7BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-7B2026.05 | 6 | 8.2 | |
| WebSailor-3BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-3B2026.05 | 2.8 | 3.8 | |
| Search-R1-14BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-14B2026.05 | 1.6 | 4.8 | |
| Search-R1-3BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-3B2026.05 | 0.8 | 2.8 | |
| Search-R1-7BMethod Strategy=Specialized Agent, Backbone=Qwen2.5-7B2026.05 | 0.4 | 3.4 |