Benchmark
GSM8K
小学数学应用题基准测试,包含8500道小学水平数学题,用于评估大语言模型的基础数学推理能力
Timeline (last 90 days)
Aug 4
GSM8K, released by OpenAI, contains approximately 8,500 elementary school math word problems designed to test multi-step reasoning ability
Unverified90%
Jul 10
MMLU包含57个学科领域约1.5万道选择题,HumanEval由OpenAI设计包含164道Python编程题,MATH包含12,500道竞赛数学题,GPQA收录研究生级别科学问题
Unverified50%