PubMedQA
Biomedical Research Q&A Dataset and Model Score Ranking List
FlagEval (Tianping) will be jointly developed by the Beijing Academy of Artificial Intelligence (BAAI) in collaboration with multiple university teams. It is a large model evaluation platform adopting a three-dimensional evaluation framework of “capability-task-indicator”, aiming to provide comprehensive and detailed evaluation results. This platform has offered a comprehensive evaluation covering more than 600 dimensions, including over 30 capabilities, 5 tasks, and 4 major categories of indicators. The task dimension includes 22 subjective and objective evaluation datasets and 84,433 questions.
Similar Sites
MMLU
Massive Multitask Language Understanding Benchmark.
CMMLU
A comprehensive large model Chinese evaluation benchmark.
MMBench
An all-round multimodal large model capability evaluation system.
C-Eval
A comprehensive Chinese basic model evaluation suite.
Open LLM Leaderboard
The open-source large model ranking list launched by Hugging Face.
OpenCompass
The large model open evaluation system launched by Shanghai AI Laboratory
HELM
The large model evaluation system launched by Stanford University.
No comments yet...