Direct Preference Optimization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
18.44LCWR
14
May 19, 2026
69.92Accuracy
11
Mar 23, 2026
91.47Accuracy
11
Mar 23, 2026
58.92Accuracy
11
Mar 23, 2026
92.8Accuracy
11
Mar 23, 2026
96.92Accuracy
11
Mar 23, 2026
85.23Accuracy
11
Mar 23, 2026
87.41Accuracy
11
Mar 23, 2026
19.85LCWR
7
May 19, 2026
20.56LCWR
7
May 19, 2026