Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific Review Generation on Human Evaluation 50 papers sampled (test)
Loading...
1,130
Actionability (Elo)
ProReviewer
902.24
961.37
1,020.5
1,079.63
Jun 11, 2026
Actionability (Elo)
Grounding (Elo)
Verifiability (Elo)
Analytical Depth (Elo)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Actionability (Elo)
Grounding (Elo)
Verifiability (Elo)
Analytical Depth (Elo)
ProReviewer
2026.06
1,130
1,296
1,181
1,210
DeepReview
2026.06
1,018
917
972
953
AgentReview
2026.06
974
969
984
984
AI-Sci-v2
2026.06
967
1,035
1,046
1,034
CycleReviewer
2026.06
911
784
818
819
Feedback
Search any
task
Search any
task