Benchmark

CleanPatrick Benchmark

What is CleanPatrick?

CleanPatrick is a large-scale, real-world image data-cleaning benchmark with 496,377 binary annotations from 933 medical crowd workers for ranking off-topic…

Released
2025-05-16
Evaluates
理解, Understanding, 安全, Safety, 大语言模型, LLM, 语言理解, Comprehension, 安全对齐, Safety Alignment, 不支持, Unsupported
Openness
restricted
Importer
OpenCompass Hub
Reported scores
0

Source provenance

CleanPatrick paper, code and dataset

No reported scores are on record for this benchmark yet.

Which sources cite CleanPatrick?

Related 理解, Understanding, 安全, Safety, 大语言模型, LLM, 语言理解, Comprehension, 安全对齐, Safety Alignment, 不支持, Unsupported benchmarks