AI EVALUATION, IN CONTEXT.BY EQUALITY MACHINE

LLM Stats

C-Eval

C-Eval is a comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. It comprises 13,948 multiple-choice questions across 52 diverse disciplines spanning humanities, science, and engineering, with four difficulty levels: middle school, high school, college, and professional. The benchmark includes C-Eval Hard, a subset of very challenging subjects requiring advanced reasoning abilities.

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 18

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
Qwen3.6 Plus0.933未收录未收录2026-04-02 · model_announcementLLM Stats
Qwen3.5-397B-A17B0.93未收录未收录2026-02-16 · model_announcementLLM Stats
Kimi K2 Base0.925未收录未收录2025-07-11 · model_announcementLLM Stats
Qwen3.5-122B-A10B0.919未收录未收录2026-02-24 · model_announcementLLM Stats
MiMo-V2.5-Pro0.915未收录未收录2026-04-27 · model_announcementLLM Stats
Qwen3.6-27B0.914未收录未收录2026-04-21 · model_announcementLLM Stats
Qwen3.5-27B0.905未收录未收录2026-02-24 · model_announcementLLM Stats
Qwen3.5-35B-A3B0.902未收录未收录2026-02-24 · model_announcementLLM Stats
Qwen3.6-35B-A3B0.9未收录未收录2026-04-16 · model_announcementLLM Stats
Kimi-k1.50.883未收录未收录2025-01-20 · model_announcementLLM Stats
Qwen3.5-9B0.882未收录未收录2026-03-02 · model_announcementLLM Stats
DeepSeek-V30.865未收录未收录2024-12-25 · model_announcementLLM Stats
Qwen3.5-4B0.851未收录未收录2026-03-02 · model_announcementLLM Stats
Qwen2 72B Instruct0.838未收录未收录2024-07-23 · model_announcementLLM Stats
Qwen2 7B Instruct0.772未收录未收录2024-07-23 · model_announcementLLM Stats
Qwen3.5-2B0.732未收录未收录2026-03-02 · model_announcementLLM Stats
Qwen3.5-0.8B0.505未收录未收录2026-03-02 · model_announcementLLM Stats
ERNIE 4.50.407未收录未收录2025-06-25 · model_announcementLLM Stats