End model evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.65Test Loss
22
Feb 26, 2026
1.146Test Loss
22
Feb 26, 2026
0.386Test Loss
22
Feb 26, 2026
0.642Test Loss
22
Feb 26, 2026
0.785Test Loss
22
Feb 26, 2026
0.103Test Loss
22
Feb 26, 2026
0.229Test Loss
22
Feb 26, 2026
0.37Test Loss
22
Feb 26, 2026
0.488Test Loss
22
Feb 26, 2026
0.258Test Loss
22
Feb 26, 2026
0.215Test Loss
22
Feb 26, 2026
0.156Test Loss
22
Feb 26, 2026
0.353Test Loss
22
Feb 26, 2026