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
LCC
QMSum
Qasper
MuSiQue
Overall
2WikiMQA
HOTpotQA
GovReport
MultiNews
NarrativeQA
RepoBench-P
MultiFieldQA
SUM
CODE
MD-QA
SD-QA
Tokens
HotpotQA
Avg.
Few.
Sgl.
Sum.
Syn.
Code.
Multi.
Model size
TrivialQA
PassageCount
MultiField-en
9 总计