Share your thoughts, 1 month free Claude Pro on usSee more

Web Browsing on BC-plus (EM, F1)

29.6EM

LongCat-Flash-Summary

Updated 6d ago

Evaluation Results

Method	Links
LongCat-Flash-Summary 2026.05		29.6	35.7
GPT-4o-ReAct 2026.05		25.2	31.6
LongCat-Flash-ReAct 2026.05		24.4	28.5
ZipRL-14B 2026.05		24.4	27
ZipRL-4B 2026.05		24	26.9
ZipRL-14B 2026.05		23.6	26.1
Gemini-3-Pro-Summary 2026.05		23.2	27.4
Gemini-3-Pro-ReAct 2026.05		22.8	27.8
ZipRL-3B 2026.05		22.5	24.8
ZipRL-8B 2026.05		20.8	23
ZipRL-7B 2026.05		19.5	21.5
GPT-4o-Summary 2026.05		17.6	27.7
WebSailor-32B 2026.05		17.6	25.6
AgentFold-4B 2026.05		15.6	19.8
AgentFold-8B 2026.05		15.6	19.3
AgentFold-14B 2026.05		14.8	16.9
Qwen3-235B-ReAct 2026.05		14	19.5
Qwen3-235B-Summary 2026.05		14	19.2
ASearcher-14B 2026.05		13.2	17.9
NestBrowse-4B 2026.05		11.2	15.7
DeepSeek-V3.2-ReAct 2026.05		8.8	13.3
NestBrowse-8B 2026.05		8.8	14.5
DeepSeek-V3.2-Summary 2026.05		7.6	11.5
NestBrowse-14B 2026.05		7.6	11.7
WebSailor-7B 2026.05		6.4	8.3
ASearcher-7B 2026.05		6	8.2
WebSailor-3B 2026.05		2.8	3.8
Search-R1-14B 2026.05		1.6	4.8
Search-R1-3B 2026.05		0.8	2.8
Search-R1-7B 2026.05		0.4	3.4