Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Paper Quality Discrimination on 74-paper ICLR NeurIPS (frontier subset)
Loading...
93
Communication Score
DeepSeek-V4 (zero-shot)
68.04
74.52
81
87.48
Jun 18, 2026
Communication Score
Confidence Score
Reviewer Score
Completeness Score
Overall Quality Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Communication Score
Confidence Score
Reviewer Score
Completeness Score
Overall Quality Score
DeepSeek-V4 (zero-shot)
System=zero-shot, mean...
2026.06
93
60
100
69
80
GPT-5.5 (OpenAIReview)
System=OpenAIReview, m...
2026.06
87
66
94
84
83
Reviewer3 (closed)
mean comments per pape...
2026.06
78
70
89
81
80
Grok-4.1-Fast ('coarse)
System='coarse, mean c...
2026.06
69
60
78
59
66
Feedback
Search any
task
Search any
task