Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Dialogue Generation on UnNI
Loading...
23.2
Rouge-L
XPERT-DeepSeek
17.9376
19.3038
20.67
22.0362
May 9, 2026
Rouge-L
Updated 21d ago
Evaluation Results
Method
Method
Links
Rouge-L
XPERT-DeepSeek
#Params=570M, #Size=di...
2026.05
23.2
XPERT-OLMoE
#Params=570M, #Size=di...
2026.05
22.6
XPERT-OLMoE
#Params=480M, #Size=di...
2026.05
21.83
XPERT-OLMoE
#Params=270M, #Size=di...
2026.05
21.55
XPERT-OLMoE
#Params=391M, #Size=di...
2026.05
21.47
Distillation
#Params=480M, #Size=di...
2026.05
21.47
XPERT-DeepSeek
#Params=270M, #Size=di...
2026.05
21.33
Scratch
#Params=480M, #Size=di...
2026.05
20.76
Distillation
#Params=270M, #Size=di...
2026.05
20.5
XPERT-DeepSeek
#Params=480M, #Size=di...
2026.05
20.48
Distillation
#Params=570M, #Size=di...
2026.05
20.27
XPERT-DeepSeek
#Params=391M, #Size=di...
2026.05
20.02
Scratch
#Params=570M, #Size=di...
2026.05
19.67
Scratch
#Params=270M, #Size=di...
2026.05
19.32
Scratch
#Params=391M, #Size=di...
2026.05
18.16
Distillation
#Params=391M, #Size=di...
2026.05
18.14
Feedback
Search any
task
Search any
task