Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Dialogue Generation on SelfInst
Loading...
11.31
Rouge-L
XPERT-OLMoE
8.19
9
9.81
10.62
May 9, 2026
Rouge-L
Updated 22d ago
Evaluation Results
Method
Method
Links
Rouge-L
XPERT-OLMoE
#Params=570M, #Size=di...
2026.05
11.31
XPERT-DeepSeek
#Params=570M, #Size=di...
2026.05
10.43
XPERT-DeepSeek
#Params=480M, #Size=di...
2026.05
10.3
Distillation
#Params=570M, #Size=di...
2026.05
10.2
XPERT-OLMoE
#Params=480M, #Size=di...
2026.05
9.57
XPERT-DeepSeek
#Params=270M, #Size=di...
2026.05
9.56
Scratch
#Params=270M, #Size=di...
2026.05
9.49
Scratch
#Params=480M, #Size=di...
2026.05
9.41
Distillation
#Params=270M, #Size=di...
2026.05
9.26
XPERT-OLMoE
#Params=391M, #Size=di...
2026.05
9.18
Distillation
#Params=480M, #Size=di...
2026.05
9.01
XPERT-DeepSeek
#Params=391M, #Size=di...
2026.05
8.72
Scratch
#Params=391M, #Size=di...
2026.05
8.5
XPERT-OLMoE
#Params=270M, #Size=di...
2026.05
8.44
Distillation
#Params=391M, #Size=di...
2026.05
8.34
Scratch
#Params=570M, #Size=di...
2026.05
8.31
Feedback
Search any
task
Search any
task