HELM
The large model evaluation system launched by Stanford University.
PubMedQA is a biomedical research question-answering dataset, which contains 1K expert-annotated, 61.2K unannotated, and 211.3K artificially generated QA instances. Currently, this leaderboard has included the medical test scores of 18 models.
Similar Sites
MMLU
Massive Multitask Language Understanding Benchmark.
CMMLU
A comprehensive large model Chinese evaluation benchmark.
FlagEval
The FlagEval (Tiancheng) large model evaluation platform launched by the Beijing Academy of Artificial Intelligence (BAAI).
OpenCompass
The large model open evaluation system launched by Shanghai AI Laboratory
Chatbot Arena
Chatbot Arena is an open platform for crowdsourced AI benchmarking.
Open LLM Leaderboard
The open-source large model ranking list launched by Hugging Face.
C-Eval
A comprehensive Chinese basic model evaluation suite.
No comments yet...