# Image Classification on CIFAR-100 90% noise (test) Source: [Image Classification on CIFAR-100 90% noise (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:27:52.242Z Evaluation of Image Classification performance on the test split of CIFAR-100 corrupted with exactly 90% noise. 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 90% noise (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 20 of 20 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | DM-AugDesc-WS-WAW | 41.2 | Not recorded | 68fa69b21e209131cea2384c | | DM-AugDesc-WS-WAW | 40.9 | Not recorded | 68fa69b21e209131cea2384c | | Li et al. \[14\] | 31.5 | Not recorded | 68fa69b21e209131cea2384c | | Li et al. \[14\] | 31 | Not recorded | 68fa69b21e209131cea2384c | | Arazo et al. | 24.3 | Not recorded | 68fa69b21e209131cea2384c | | Arazo et al. | 20.5 | Not recorded | 68fa69b21e209131cea2384c | | Li et al. \[15\] | 19.5 | Not recorded | 68fa69b21e209131cea2384c | | DM-AugDesc-WS-SAW | 17.3 | Not recorded | 68fa69b21e209131cea2384c | | Yi & Wu | 15.3 | Not recorded | 68fa69b21e209131cea2384c | | DM-AugDesc-WS-SAW | 15.1 | Not recorded | 68fa69b21e209131cea2384c | | Zhang et al. | 14.6 | Not recorded | 68fa69b21e209131cea2384c | | Li et al. \[15\] | 14.3 | Not recorded | 68fa69b21e209131cea2384c | | Yu et al. | 13.7 | Not recorded | 68fa69b21e209131cea2384c | | Reed et al. | 10.2 | Not recorded | 68fa69b21e209131cea2384c | | Cross-Entropy | 10.1 | Not recorded | 68fa69b21e209131cea2384c | | Yu et al. | 8.8 | Not recorded | 68fa69b21e209131cea2384c | | Yi & Wu | 8.8 | Not recorded | 68fa69b21e209131cea2384c | | Zhang et al. | 8.1 | Not recorded | 68fa69b21e209131cea2384c | | Reed et al. | 3.8 | Not recorded | 68fa69b21e209131cea2384c | | Cross-Entropy | 3.5 | Not recorded | 68fa69b21e209131cea2384c | ### DM-AugDesc-WS-WAW Accuracy: 41.2. Result ID: 698dd794ffc3901de09902e0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Best"}. This record does not assert independent reproduction. ### DM-AugDesc-WS-WAW Accuracy: 40.9. Result ID: 698dd794ffc3901de09902e1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Last"}. This record does not assert independent reproduction. ### Li et al. \[14\] Accuracy: 31.5. Result ID: 698dd794ffc3901de09902dc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Best"}. This record does not assert independent reproduction. ### Li et al. \[14\] Accuracy: 31. Result ID: 698dd794ffc3901de09902dd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Last"}. This record does not assert independent reproduction. ### Arazo et al. Accuracy: 24.3. Result ID: 698dd794ffc3901de09902da. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Best"}. This record does not assert independent reproduction. ### Arazo et al. Accuracy: 20.5. Result ID: 698dd794ffc3901de09902db. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Last"}. This record does not assert independent reproduction. ### Li et al. \[15\] Accuracy: 19.5. Result ID: 698dd794ffc3901de09902d8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Best"}. This record does not assert independent reproduction. ### DM-AugDesc-WS-SAW Accuracy: 17.3. Result ID: 698dd794ffc3901de09902de. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Best"}. This record does not assert independent reproduction. ### Yi & Wu Accuracy: 15.3. Result ID: 698dd794ffc3901de09902d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Selection":"Best"}. This record does not assert independent reproduction. ### DM-AugDesc-WS-SAW Accuracy: 15.1. Result ID: 698dd794ffc3901de09902df. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Last"}. This record does not assert independent reproduction. ### Zhang et al. Accuracy: 14.6. Result ID: 698dd794ffc3901de09902d4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Best"}. This record does not assert independent reproduction. ### Li et al. \[15\] Accuracy: 14.3. Result ID: 698dd794ffc3901de09902d9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Last"}. This record does not assert independent reproduction. ### Yu et al. Accuracy: 13.7. Result ID: 698dd794ffc3901de09902d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Selection":"Best"}. This record does not assert independent reproduction. ### Reed et al. Accuracy: 10.2. Result ID: 698dd794ffc3901de09902d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Selection":"Best"}. This record does not assert independent reproduction. ### Cross-Entropy Accuracy: 10.1. Result ID: 698dd794ffc3901de09902ce. [Reporting paper]() Recorded evaluation configuration: {"Model Selection":"Best"}. This record does not assert independent reproduction. ### Yu et al. Accuracy: 8.8. Result ID: 698dd794ffc3901de09902d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Selection":"Last"}. This record does not assert independent reproduction. ### Yi & Wu Accuracy: 8.8. Result ID: 698dd794ffc3901de09902d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Selection":"Last"}. This record does not assert independent reproduction. ### Zhang et al. Accuracy: 8.1. Result ID: 698dd794ffc3901de09902d5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Selection":"Last"}. This record does not assert independent reproduction. ### Reed et al. Accuracy: 3.8. Result ID: 698dd794ffc3901de09902d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Selection":"Last"}. This record does not assert independent reproduction. ### Cross-Entropy Accuracy: 3.5. Result ID: 698dd794ffc3901de09902cf. [Reporting paper]() Recorded evaluation configuration: {"Model Selection":"Last"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.