AI EVALUATION, IN CONTEXT.BY EQUALITY MACHINE

LLM Stats

BrowseComp-zh

A high-difficulty benchmark purpose-built to comprehensively evaluate LLM agents on the Chinese web, consisting of 289 multi-hop questions spanning 11 diverse domains including Film & TV, Technology, Medicine, and History. Questions are reverse-engineered from short, objective, and easily verifiable answers, requiring sophisticated reasoning and information reconciliation beyond basic retrieval. The benchmark addresses linguistic, infrastructural, and censorship-related complexities in Chinese web environments.

评测信息与证据

来源
LLM Stats
发布者
未收录
评测发布日期
未收录
采集日期
2026-08-17
模态
text

本站保留来源报告的结果,不代表独立复测。请先核对任务版本、评测协议、分数单位和报告日期;不同运行条件不能直接合并为统一排名。

原始资料

报告成绩 13

按来源中的观察顺序展示,顺序不代表排名。日期保留原始精度。

模型数值单位协议报告日期与口径来源
Qwen3.5-397B-A17B0.703未收录未收录2026-02-16 · model_announcementLLM Stats
Qwen3.5-122B-A10B0.699未收录未收录2026-02-24 · model_announcementLLM Stats
Qwen3.5-35B-A3B0.695未收录未收录2026-02-24 · model_announcementLLM Stats
LongCat-Flash-Thinking-26010.69未收录未收录2026-01-14 · model_announcementLLM Stats
GLM-4.70.666未收录未收录2025-12-22 · model_announcementLLM Stats
DeepSeek-V3.2 (Thinking)0.65未收录未收录2025-12-01 · model_announcementLLM Stats
DeepSeek-V3.20.65未收录未收录2025-12-01 · model_announcementLLM Stats
Kimi K2-Thinking-09050.623未收录未收录2025-09-05 · model_announcementLLM Stats
Qwen3.5-27B0.621未收录未收录2026-02-24 · model_announcementLLM Stats
DeepSeek-V3.10.492未收录未收录2025-01-10 · model_announcementLLM Stats
MiniMax M20.485未收录未收录2025-10-27 · model_announcementLLM Stats
DeepSeek-V3.2-Exp0.479未收录未收录2025-09-29 · model_announcementLLM Stats
DeepSeek-R1-05280.357未收录未收录2025-05-28 · model_announcementLLM Stats