llm-benchmarks

MMLU stands for Massive Multitask Language Underst...

Open LLM Leaderboard is a platform provided by Hug...

C-Eval is a multi-level, multi-subject Chinese eva...

FlagEval is a scientific, fair, and open evaluatio...

SuperCLUE is a comprehensive benchmark for evaluat...

AGI-Eval is an LLM evaluation community co-publish...

OpenCompass is an open evaluation framework from t...

CMMLU is a comprehensive benchmark designed to eva...

MMBench is a multimodal benchmark jointly develope...

HELM is a large model evaluation framework from St...

LMArena is an AI model evaluation platform develop...

LLMEval3 is a large language model evaluation benc...

H2O Eval Studio is a tool from H2O.ai designed to ...

PubMedQA is a question-answering dataset designed ...

AI Ping (New) is a comprehensive evaluation and in...

AI Ping is a platform focused on AI large model se...