Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Open Set Recognition research benchmarks – Page 2 · SOTA2 Research

Open Set Recognition

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

BloodMNIST t=5 (test)

98.5Accuracy

8

May 4, 2026

CIFAR100 80 known / 20 unknown

86.8AUROC

8

Feb 26, 2026

CIFAR100 55 known / 45 unknown

0.87AUROC

8

Feb 26, 2026

BreaKHis t=5 (test)

93.68Accuracy

7

May 4, 2026

DermaMNIST v=2 (test)

86.82Accuracy

7

May 4, 2026

ImageNet 1k (test)

57.8C-F1

5

Feb 26, 2026

WebVision1k (test)

62.2C-F1

5

Feb 26, 2026

C+50 (CIFAR10 with 50 unseen classes) (test)

74.6F1 Score

4

Feb 26, 2026

CIFAR10 C+10 10 unseen classes (test)

79.38F1 Score

4

Feb 26, 2026

72.63F1 Score

4

Feb 26, 2026

79.25F1 Score

4

Feb 26, 2026

91.37F1 Score

4

Feb 26, 2026

Caltech-UCSD-Birds (CUB) Hard split 42 (test)

0.908Closed-set Accuracy

2

Feb 26, 2026

ImageNet Semantic Shift Benchmark Hard

78.8Accuracy

2

Feb 26, 2026

ImageNet Easy Semantic Shift Benchmark

78.8Accuracy

2

Feb 26, 2026

FGVC-Aircraft Semantic Shift Benchmark (Hard)

0.917Accuracy

2

Feb 26, 2026

FGVC-Aircraft Semantic Shift Benchmark (Easy)

91.7Accuracy

2

Feb 26, 2026

SCars Semantic Shift Benchmark (Hard)

97.1Accuracy

2

Feb 26, 2026

SCars Semantic Shift Benchmark (Easy)

97.1Accuracy

2

Feb 26, 2026

CUB Semantic Shift Benchmark (Hard)

86.2Accuracy

2

Feb 26, 2026

CUB Semantic Shift Benchmark (Easy)

86.2Accuracy

2

Feb 26, 2026

Page 2 of 2

Popular datasets

CIFAR ImageNet CUB MNIST SVHN

Follow for updates

Join SOTA2 Contact