Language Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
58.16Accuracy
4
Feb 26, 2026
88.93Accuracy
3
Jun 2, 2026
92.63Accuracy
3
Jun 2, 2026
35.09Accuracy
3
May 14, 2026
24.09Accuracy
3
May 14, 2026
28Accuracy
3
May 14, 2026
26.99Accuracy
3
May 14, 2026
25.05Accuracy (INCLUDE hi)
3
May 14, 2026
24.31Accuracy
3
May 12, 2026
80.38Mean Accuracy (±STD)
3
May 8, 2026
86Accuracy
3
May 7, 2026
61.8Normalized Log Accuracy
3
Mar 18, 2026
44.86Accuracy
3
Mar 6, 2026
43.51Accuracy
3
Mar 6, 2026
0.15Cost ($)
3
Feb 26, 2026
68.2Non-Eng AVG Original Accuracy (0-shot)
3
Feb 26, 2026
48.2Baseline Accuracy
3
Feb 26, 2026
71.3Baseline Acc
3
Feb 26, 2026
35.04Accuracy
3
Feb 26, 2026
48.81Humanities Score
3
Feb 26, 2026
17Score
3
Feb 26, 2026
27.72Accuracy (Humanities)
3
Feb 26, 2026
84Accuracy
3
Feb 26, 2026
44.1Accuracy
3
Feb 26, 2026
17.58Accuracy
2
Mar 20, 2026