# Image Classification on CIFAR-100 (test) (Direct and Transfer Error Rates) Source: [Image Classification on CIFAR-100 (test) (Direct and Transfer Error Rates)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:17.121Z Evaluation of Image Classification performance on the CIFAR-100 test set, reporting standard error rate alongside specific direct and transfer error rate measurements. 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 | Test Error Rate | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 23 of 23 | | 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 - [Test Error Rate](): Lower is better; unit: PERCENT. - [Transfer Test Error Rate](): Lower is better; unit: PERCENT. - [Direct Test Error Rate](): Lower is better; unit: PERCENT. ## Recorded results | Method | Test Error Rate | Result date | Report paper | | --- | --- | --- | --- | | AA | 10.7 | Not recorded | 68fa66e21e209131cea12d0c | | PBA | 10.9 | Not recorded | 68fa66e21e209131cea12d0c | | Cutout | 12.2 | Not recorded | 68fa66e21e209131cea12d0c | | Baseline | 14 | Not recorded | 68fa66e21e209131cea12d0c | | AA | 14.3 | Not recorded | 68fa66e21e209131cea12d0c | | PBA | 15.3 | Not recorded | 68fa66e21e209131cea12d0c | | Cutout | 16 | Not recorded | 68fa66e21e209131cea12d0c | | PBA | 16.7 | Not recorded | 68fa66e21e209131cea12d0c | | AA | 17.1 | Not recorded | 68fa66e21e209131cea12d0c | | Baseline | 17.1 | Not recorded | 68fa66e21e209131cea12d0c | | Cutout | 18.4 | Not recorded | 68fa66e21e209131cea12d0c | | Baseline | 18.8 | Not recorded | 68fa66e21e209131cea12d0c | | AA | 20.7 | Not recorded | 68fa66e21e209131cea12d0c | | Cutout | 25.2 | Not recorded | 68fa66e21e209131cea12d0c | | Baseline | 26 | Not recorded | 68fa66e21e209131cea12d0c | ### AA Test Error Rate: 10.7. Result ID: 698d0d368b517eb4331ea038. [Reporting paper]() Recorded evaluation configuration: {"Model":"PyramidNet+ShakeDrop"}. This record does not assert independent reproduction. ### PBA Test Error Rate: 10.9. Result ID: 698d0d368b517eb4331ea039. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"PyramidNet+ShakeDrop"}. This record does not assert independent reproduction. ### Cutout Test Error Rate: 12.2. Result ID: 698d0d368b517eb4331ea037. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"PyramidNet+ShakeDrop"}. This record does not assert independent reproduction. ### Baseline Test Error Rate: 14. Result ID: 698d0d368b517eb4331ea036. [Reporting paper]() Recorded evaluation configuration: {"Model":"PyramidNet+ShakeDrop"}. This record does not assert independent reproduction. ### AA Test Error Rate: 14.3. Result ID: 698d0d368b517eb4331ea032. [Reporting paper]() Recorded evaluation configuration: {"Model":"Shake-Shake(26 2x96d)"}. This record does not assert independent reproduction. ### PBA Test Error Rate: 15.3. Result ID: 698d0d368b517eb4331ea033. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Shake-Shake(26 2x96d)"}. This record does not assert independent reproduction. ### Cutout Test Error Rate: 16. Result ID: 698d0d368b517eb4331ea031. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Shake-Shake(26 2x96d)"}. This record does not assert independent reproduction. ### PBA Test Error Rate: 16.7. Result ID: 698d0d368b517eb4331ea02d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Wide-ResNet-28-10"}. This record does not assert independent reproduction. ### AA Test Error Rate: 17.1. Result ID: 698d0d368b517eb4331ea02c. [Reporting paper]() Recorded evaluation configuration: {"Model":"Wide-ResNet-28-10"}. This record does not assert independent reproduction. ### Baseline Test Error Rate: 17.1. Result ID: 698d0d368b517eb4331ea030. [Reporting paper]() Recorded evaluation configuration: {"Model":"Shake-Shake(26 2x96d)"}. This record does not assert independent reproduction. ### Cutout Test Error Rate: 18.4. Result ID: 698d0d368b517eb4331ea02b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Wide-ResNet-28-10"}. This record does not assert independent reproduction. ### Baseline Test Error Rate: 18.8. Result ID: 698d0d368b517eb4331ea02a. [Reporting paper]() Recorded evaluation configuration: {"Model":"Wide-ResNet-28-10"}. This record does not assert independent reproduction. ### AA Test Error Rate: 20.7. Result ID: 698d0d368b517eb4331ea027. [Reporting paper]() Recorded evaluation configuration: {"Model":"Wide-ResNet-40-2"}. This record does not assert independent reproduction. ### Cutout Test Error Rate: 25.2. Result ID: 698d0d368b517eb4331ea026. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Wide-ResNet-40-2"}. This record does not assert independent reproduction. ### Baseline Test Error Rate: 26. Result ID: 698d0d368b517eb4331ea025. [Reporting paper]() Recorded evaluation configuration: {"Model":"Wide-ResNet-40-2"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.