# Image Classification on CIFAR-100 (test) (Standard and Robust Accuracy) Source: [Image Classification on CIFAR-100 (test) (Standard and Robust Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:04:45.263Z Evaluation of Image Classification performance on the CIFAR-100 test set, reporting both standard accuracy and a general measure of robustness accuracy. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Image Classification | | Dataset (including any stated split) | CIFAR-100 (test) | | Metric | Standard Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Standard Accuracy](): Higher is better; unit: PERCENT. - [Robust Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Standard Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Wang et al. | 75.22 | Not recorded | 68fa71671e209131cea5138a | | Wang et al. | 72.58 | Not recorded | 68fa71671e209131cea5138a | | Debenedetti et al. | 70.76 | Not recorded | 68fa71671e209131cea5138a | | Debenedetti et al. | 69.21 | Not recorded | 68fa71671e209131cea5138a | | Gowal et al. | 69.15 | Not recorded | 68fa71671e209131cea5138a | | Pang et al. | 65.56 | Not recorded | 68fa71671e209131cea5138a | | Pang et al. | 63.66 | Not recorded | 68fa71671e209131cea5138a | | Rebuffi et al. | 63.56 | Not recorded | 68fa71671e209131cea5138a | | Rebuffi et al. | 62.41 | Not recorded | 68fa71671e209131cea5138a | ### Wang et al. Standard Accuracy: 75.22. Result ID: 6991ce3f3a6c3148490ab2ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier":"WideResNet-70-16","Extra data":false}. This record does not assert independent reproduction. ### Wang et al. Standard Accuracy: 72.58. Result ID: 6991ce3f3a6c3148490ab2ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier":"WideResNet-28-10","Extra data":false}. This record does not assert independent reproduction. ### Debenedetti et al. Standard Accuracy: 70.76. Result ID: 6991ce3f3a6c3148490ab2a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier":"XCIT-L12","Extra data":true}. This record does not assert independent reproduction. ### Debenedetti et al. Standard Accuracy: 69.21. Result ID: 6991ce3f3a6c3148490ab2a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier":"XCIT-M12","Extra data":true}. This record does not assert independent reproduction. ### Gowal et al. Standard Accuracy: 69.15. Result ID: 6991ce3f3a6c3148490ab2a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier":"WideResNet-70-16","Extra data":true}. This record does not assert independent reproduction. ### Pang et al. Standard Accuracy: 65.56. Result ID: 6991ce3f3a6c3148490ab2ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier":"WideResNet-70-16","Extra data":false}. This record does not assert independent reproduction. ### Pang et al. Standard Accuracy: 63.66. Result ID: 6991ce3f3a6c3148490ab2a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier":"WideResNet-28-10","Extra data":false}. This record does not assert independent reproduction. ### Rebuffi et al. Standard Accuracy: 63.56. Result ID: 6991ce3f3a6c3148490ab2ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier":"WideResNet-70-16","Extra data":false}. This record does not assert independent reproduction. ### Rebuffi et al. Standard Accuracy: 62.41. Result ID: 6991ce3f3a6c3148490ab2aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Classifier":"WideResNet-28-10","Extra data":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.