Addition
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.56Token Accuracy
14
Jun 4, 2026
95.47Token Accuracy
7
Jun 4, 2026
99.5Accuracy
7
Feb 26, 2026
0.016Skill 1 Score
7
Feb 26, 2026
0.64RMSE [0, 10^2]
5
Mar 6, 2026
99.9Per-Char Accuracy
4
Feb 26, 2026
59.81Task Accuracy
3
May 18, 2026
96.97Task Accuracy
3
May 18, 2026
100Accuracy
3
May 6, 2026
28.57Task Accuracy
1
May 18, 2026