Peer Review Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
71.65Accuracy
8
Mar 11, 2026
66.1Accuracy
8
Mar 11, 2026
70.29Accuracy
8
Mar 11, 2026
47.851Most Constructive
4
Jun 23, 2026
69.77DeepReviewer 2.0 Win Rate
1
Apr 14, 2026
86.05DeepReviewer 2.0 Win Rate
1
Apr 14, 2026
58.14DeepReviewer 2.0 Win Rate
1
Apr 14, 2026
84.5DeepReviewer 2.0 Win Rate
1
Apr 14, 2026
59.69DeepReviewer 2.0 Win Rate
1
Apr 14, 2026
71.63DeepReviewer 2.0 Win Rate
1
Apr 14, 2026