Skill Evolution
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
59Accuracy
40
May 27, 2026
54.8Accuracy
40
May 27, 2026
77.3Accuracy
40
May 27, 2026
92.78Best@20
1
May 28, 2026
77.7Best@20
1
May 28, 2026
92.96Best@20
1
May 28, 2026
93.67Best@20
1
May 28, 2026
86.67Best@20
1
May 28, 2026