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

w/ DARE
w/o DARE
CSQA
OBQA
PIQA
Wino
ARC-C
ARC-E
GSM8K
HSwag
TriQA
Toxigen
Diff Avg
Diff Std
1
5
10
20
30
40
50
0.1
0.3
0.5
0.7
1.0
6 行 总计