Reward Modeling
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
61.11Chile Score
7
Jun 18, 2026
61.35Communication Score
7
Jun 8, 2026
90Accuracy (%)
7
May 29, 2026
95.7Correlation
7
May 1, 2026
0.451User SROCC
7
Apr 10, 2026
61.8Accuracy
7
Apr 2, 2026
61.6Accuracy
7
Apr 2, 2026
62.1Accuracy
7
Apr 2, 2026
62.9Accuracy
7
Apr 2, 2026
62.4Accuracy
7
Apr 2, 2026
63.3Accuracy
7
Apr 2, 2026
61.5Accuracy
7
Apr 2, 2026
96.6Accuracy
7
Apr 2, 2026
96.4Accuracy
7
Apr 2, 2026
96.8Accuracy
7
Apr 2, 2026
95.1Accuracy
7
Apr 2, 2026
94.7Accuracy
7
Apr 2, 2026
95.5Accuracy
7
Apr 2, 2026
95.3Accuracy
7
Apr 2, 2026
95.1Accuracy
7
Apr 2, 2026
95.6Accuracy
7
Apr 2, 2026
88.5Precision
7
Feb 26, 2026
61.9Precision
7
Feb 26, 2026
94Precision
7
Feb 26, 2026
79.2Precision
7
Feb 26, 2026