Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Infilling on ROCStories Infill 1/5
Loading...
14.5
ROUGE-1
MDLM
7.948
9.649
11.35
13.051
Jul 2, 2026
ROUGE-1
ROUGE-2
ROUGE-L
Tput
Updated 23d ago
Evaluation Results
Method
Method
Links
ROUGE-1
ROUGE-2
ROUGE-L
Tput
MDLM
Size=130M, Tokens=157B
2026.07
14.5
1.6
13.3
71.9
DiffuGPT-S
Size=127M, Tokens=n/a
2026.07
14
1.5
13
-
ASSD
Size=110M, Tokens=45B
2026.07
13.1
1.1
12
-
SEDD-S
Size=170M, Tokens=210B
2026.07
11.6
0.8
10.7
-
SW-SetDLM S ≤ 32
Size=110M, Tokens=157B
2026.07
11.6
1
10.9
132
GPT2-S
Size=127M, Tokens=n/a
2026.07
9.5
0.4
8.7
-
BD3LM S = 16
Size=110M, Tokens=157B
2026.07
9.2
0.6
8.6
105.8
AR Transformer
Size=130M, Tokens=157B
2026.07
8.2
0.5
7.6
159.7
Feedback
Search any
task
Search any
task