HyperAIHyperAI

Command Palette

Search for a command to run...

各模型在此基准测试上的性能结果

指标

avg
New-avg
Old-avg
New (MMLU)
Old (MMLU)
New (ARC-C)
Old (ARC-C)
Expand-params
New (Belebele)
Old (Belebele)
New (Hellaswag)
Old (Hellaswag)
1 总计