Language
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
86.51Score
30
Feb 26, 2026
85.56Score
20
Feb 26, 2026
84.2Accuracy
6
May 20, 2026
0.433Accuracy
3
Feb 26, 2026
59.4Accuracy
3
Feb 26, 2026
205Peak Performance (FP4/FP8)
1
Feb 26, 2026
2.05Peak Performance
1
Feb 26, 2026