# Image Classification on CIFAR-10 (test) (Clean Accuracy and CRA Robustness) Source: [Image Classification on CIFAR-10 (test) (Clean Accuracy and CRA Robustness)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:39:18.532Z Evaluation of Image Classification performance on the CIFAR-10 test set, focusing on standard Clean Accuracy and Corruption Robustness Accuracy (CRA) measured under varying levels of input corruption (noise levels 36/255, 72/255, and 108/255). 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-10 (test) | | Metric | Clean Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [Clean Accuracy](): Higher is better; unit: PERCENT. - [CRA (Noise 36/255)](): Higher is better; unit: PERCENT. - [CRA (Noise 72/255)](): Higher is better; unit: PERCENT. - [CRA (Noise 108/255)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Clean Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LipNeXt L32W2048 | 85 | Not recorded | 697846dfa2b28e761d87c821 | | BRONet | 81.6 | Not recorded | 697846dfa2b28e761d87c821 | | LipNeXt L32W1024 | 81.5 | Not recorded | 697846dfa2b28e761d87c821 | | LiResNet | 81 | Not recorded | 697846dfa2b28e761d87c821 | | CPL XL | 78.5 | Not recorded | 697846dfa2b28e761d87c821 | | LOT-20 | 77.1 | Not recorded | 697846dfa2b28e761d87c821 | | SOC-20 | 76.3 | Not recorded | 697846dfa2b28e761d87c821 | | Cayley Large | 74.6 | Not recorded | 697846dfa2b28e761d87c821 | | SLL X-Large | 73.3 | Not recorded | 697846dfa2b28e761d87c821 | | AOL Large | 71.6 | Not recorded | 697846dfa2b28e761d87c821 | ### LipNeXt L32W2048 Clean Accuracy: 85. Result ID: 6999158b5698665ec47bae75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Param.":"256M"}. This record does not assert independent reproduction. ### BRONet Clean Accuracy: 81.6. Result ID: 6999158b5698665ec47bae73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Param.":"68M"}. This record does not assert independent reproduction. ### LipNeXt L32W1024 Clean Accuracy: 81.5. Result ID: 6999158b5698665ec47bae74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Param.":"64M"}. This record does not assert independent reproduction. ### LiResNet Clean Accuracy: 81. Result ID: 6999158b5698665ec47bae72. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Param.":"83M"}. This record does not assert independent reproduction. ### CPL XL Clean Accuracy: 78.5. Result ID: 6999158b5698665ec47bae6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Param.":"236M"}. This record does not assert independent reproduction. ### LOT-20 Clean Accuracy: 77.1. Result ID: 6999158b5698665ec47bae6e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Param.":"18M"}. This record does not assert independent reproduction. ### SOC-20 Clean Accuracy: 76.3. Result ID: 6999158b5698665ec47bae6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Param.":"27M"}. This record does not assert independent reproduction. ### Cayley Large Clean Accuracy: 74.6. Result ID: 6999158b5698665ec47bae6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Param.":"21M"}. This record does not assert independent reproduction. ### SLL X-Large Clean Accuracy: 73.3. Result ID: 6999158b5698665ec47bae71. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#Param.":"236M"}. This record does not assert independent reproduction. ### AOL Large Clean Accuracy: 71.6. Result ID: 6999158b5698665ec47bae70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#Param.":"136M"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.