CLUE benchmark

icon indicating a website link www.CLUEbenchmarks.com icon indicating an email [email protected]

icon location Organization of Language Understanding Evaluation benchmark for Chinese: tasks & datasets, baselines, pre-trained Chinese models, corpus and leaderboard

Results 30 repositories owned by CLUE benchmark

QBQTC

52
Stars
7
Forks
Watchers

QBQTC: 大规模搜索匹配数据集

verified publisher icon CLUEbenchmark

ZeroCLUE

53
Stars
8
Forks
Watchers

零样本学习测评基准，中文版

verified publisher icon CLUEbenchmark

SuperCLUE

2.9k
Stars
93
Forks
Watchers

SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese

verified publisher icon CLUEbenchmark

SuperCLUE-Llama2-Chinese

127
Stars
8
Forks
Watchers

Llama2开源模型中文版-全方位测评，基于SuperCLUE的OPEN基准 | Llama2 Chinese evaluation with SuperCLUE

verified publisher icon CLUEbenchmark

LGEB

16
Stars
1
Forks
Watchers

LGEB: Benchmark of Language Generation Evaluation

verified publisher icon CLUEbenchmark

SuperCLUE-Agent

59
Stars
1
Forks
Watchers

SuperCLUE-Agent: 基于中文原生任务的Agent智能体核心能力测评基准

verified publisher icon CLUEbenchmark

SuperCLUE-Math6

17
Stars
2
Forks
Watchers

SuperCLUE-Math6：新一代中文原生多轮多步数学推理数据集的探索之旅

verified publisher icon CLUEbenchmark

SuperCLUE-Open

66
Stars
3
Forks
Watchers

中文通用大模型开放域多轮测评基准 | An Open Domain Benchmark for Foundation Models in Chinese

verified publisher icon CLUEbenchmark

SuperCLUE-Safety

66
Stars
3
Forks
Watchers

SC-Safety: 中文大模型多轮对抗安全基准

verified publisher icon CLUEbenchmark

SuperCLUElyb

137
Stars
4
Forks
Watchers

SuperCLUE琅琊榜：中文通用大模型匿名对战评价基准

verified publisher icon CLUEbenchmark