AI EVALUATION, IN CONTEXT.BY EQUALITY MACHINE

LLM Stats

ZebraLogic

ZebraLogic is an evaluation framework for assessing large language models' logical reasoning capabilities through logic grid puzzles derived from constraint satisfaction problems (CSPs). The benchmark consists of 1,000 programmatically generated puzzles with controllable and quantifiable complexity, revealing a 'curse of complexity' where model accuracy declines significantly as problem complexity grows.

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 8

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 VL 235B A22B Thinking0.973未收录未收录2025-09-22 · model_announcementLLM Stats
LongCat-Flash-Thinking0.955未收录未收录2025-09-22 · model_announcementLLM Stats
Qwen3-235B-A22B-Instruct-25070.95未收录未收录2025-07-22 · model_announcementLLM Stats
LongCat-Flash-Chat0.893未收录未收录2025-08-29 · model_announcementLLM Stats
Kimi K2-Instruct-09050.89未收录未收录2025-09-05 · model_announcementLLM Stats
Kimi K2 Instruct0.89未收录未收录2025-07-11 · model_announcementLLM Stats
MiniMax M1 80K0.868未收录未收录2025-06-16 · model_announcementLLM Stats
MiniMax M1 40K0.801未收录未收录2025-06-16 · model_announcementLLM Stats