Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Review Generation on FIRSTPASS n = 372 (test)
Loading...
2,155
Review Length
Human reference
473.32
909.91
1,346.5
1,783.09
Jun 18, 2026
Review Length
ROUGE-1 Score
ROUGE-2 Score
ROUGE-L Score
Significance (p-value)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Review Length
ROUGE-1 Score
ROUGE-2 Score
ROUGE-L Score
Significance (p-value)
Human reference
2026.06
2,155
-
-
-
-
FIRSTPASS
Protocol=SFT
2026.06
1,187
35.4
8.8
15.4
-
Qwen2.5-7B
Protocol=zero-shot
2026.06
1,019
37.3
9
13.6
0.001
Llama-3-8B
Protocol=zero-shot
2026.06
1,006
39.1
10.2
16.4
0.001
Gemini-3.1-flash-lite-preview
Protocol=ZS
2026.06
934
39.9
10.9
14.6
0.001
DeepSeek-R1-7B
Protocol=zero-shot
2026.06
538
27.7
6.8
11.6
0.001
Feedback
Search any
task
Search any
task