Classification
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
69.2Accuracy
17
Feb 26, 2026
0.343NLL
17
May 18, 2026
0.332NLL
17
May 18, 2026
98.4Accuracy (Original IN-9)
17
Apr 2, 2026
98.65Acc
17
Feb 26, 2026
77.4Accuracy (5-shot)
17
Feb 26, 2026
73.5MCA_u
17
Feb 26, 2026
61.59Test Accuracy
17
Feb 26, 2026
43.45Test Accuracy
17
Feb 26, 2026
98.97Accuracy
17
Feb 26, 2026
74.6AUPRC
17
Feb 26, 2026
99Accuracy
17
Apr 29, 2026
53.19Micro-F1
17
Feb 26, 2026
69.55Micro F1
17
Feb 26, 2026
98.59Accuracy
17
May 25, 2026
82.85Mean Accuracy
16
Jul 9, 2026
94.59Accuracy (%)
16
Jun 23, 2026
76.2Accuracy
16
Jun 16, 2026
1Average Rank
16
Jun 8, 2026
4.34ECE
16
Jun 5, 2026
2.96ECE
16
Jun 5, 2026
2.21Expected Calibration Error (ECE)
16
Jun 5, 2026
2.38ECE
16
Jun 5, 2026
3.9ECE
16
Jun 5, 2026
1.85ECE
16
Jun 5, 2026