ResearchBenchmarksImage Classification on CIFAR-10 (test) (Accuracy, Calibration, and Robustness Metrics)Follow97.88AccuracyViT-B-1697.141697.333397.52597.7167Feb 9, 2026Evaluation ResultsMethodMethodLinksAccuracyMCCAURCAUROCFPR@95ECENLLBrier ScoreViT-B-16#params=86M, training_...#params=86M, training_context=fine-tuned on CIFAR-10 from ImageNet2026.0297.8897.880.14195.62419.3418.0212.5646.843DIRECTOR#params=50M, training_...#params=50M, training_context=fine-tuned on CIFAR-10 from ImageNet2026.0297.1797.170.21294.88128.6221.6111.1224.762