# Image Classification on CIFAR-10 (test) (Symmetric/Asymmetric Accuracy Thresholds) Source: [Image Classification on CIFAR-10 (test) (Symmetric/Asymmetric Accuracy Thresholds)]() Collection index: [llms.txt]() Data updated: 2026-03-10T13:02:17.232Z Evaluation of Image Classification performance on the CIFAR-10 test set, reporting accuracy at specific symmetric (20%, 50%, 80%, 90%) and asymmetric (40%) thresholds. 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 | Accuracy (Sym. 20%) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 (Sym. 20%)](): Higher is better; unit: PERCENT. - [Accuracy (Sym. 50%)](): Higher is better; unit: PERCENT. - [Accuracy (Sym. 80%)](): Higher is better; unit: PERCENT. - [Accuracy (Sym. 90%)](): Higher is better; unit: PERCENT. - [Accuracy (Asym. 40%)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Sym. 20%) | Result date | Report paper | | --- | --- | --- | --- | | ProMix | 97.7 | Not recorded | 69afa56c2d603e6de3e43902 | | ProMix | 97.6 | Not recorded | 69afa56c2d603e6de3e43902 | | ACD-U | 97.2 | Not recorded | 69afa56c2d603e6de3e43902 | | Semi-RML++ | 97.1 | Not recorded | 69afa56c2d603e6de3e43902 | | ACD-U | 97 | Not recorded | 69afa56c2d603e6de3e43902 | | SV-Learner | 96.9 | Not recorded | 69afa56c2d603e6de3e43902 | | NoiseBox+SS-KNN | 96.6 | Not recorded | 69afa56c2d603e6de3e43902 | | RankMatch | 96.5 | Not recorded | 69afa56c2d603e6de3e43902 | | RankMatch | 96.4 | Not recorded | 69afa56c2d603e6de3e43902 | | LongReMix | 96.3 | Not recorded | 69afa56c2d603e6de3e43902 | | DivideMix | 96.1 | Not recorded | 69afa56c2d603e6de3e43902 | | LongReMix | 96 | Not recorded | 69afa56c2d603e6de3e43902 | | CLIPCleaner | 95.9 | Not recorded | 69afa56c2d603e6de3e43902 | | DivideMix | 95.7 | Not recorded | 69afa56c2d603e6de3e43902 | ### ProMix Accuracy (Sym. 20%): 97.7. Result ID: 69b0153b6dbb7075b95a17c8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Best"}. This record does not assert independent reproduction. ### ProMix Accuracy (Sym. 20%): 97.6. Result ID: 69b0153b6dbb7075b95a17c9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Last"}. This record does not assert independent reproduction. ### ACD-U Accuracy (Sym. 20%): 97.2. Result ID: 69b0153b6dbb7075b95a17d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Best"}. This record does not assert independent reproduction. ### Semi-RML++ Accuracy (Sym. 20%): 97.1. Result ID: 69b0153b6dbb7075b95a17ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Last"}. This record does not assert independent reproduction. ### ACD-U Accuracy (Sym. 20%): 97. Result ID: 69b0153b6dbb7075b95a17d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Last"}. This record does not assert independent reproduction. ### SV-Learner Accuracy (Sym. 20%): 96.9. Result ID: 69b0153b6dbb7075b95a17cc. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Best"}. This record does not assert independent reproduction. ### NoiseBox+SS-KNN Accuracy (Sym. 20%): 96.6. Result ID: 69b0153b6dbb7075b95a17cd. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Last"}. This record does not assert independent reproduction. ### RankMatch Accuracy (Sym. 20%): 96.5. Result ID: 69b0153b6dbb7075b95a17ca. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Best"}. This record does not assert independent reproduction. ### RankMatch Accuracy (Sym. 20%): 96.4. Result ID: 69b0153b6dbb7075b95a17cb. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Last"}. This record does not assert independent reproduction. ### LongReMix Accuracy (Sym. 20%): 96.3. Result ID: 69b0153b6dbb7075b95a17c6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Best"}. This record does not assert independent reproduction. ### DivideMix Accuracy (Sym. 20%): 96.1. Result ID: 69b0153b6dbb7075b95a17c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Best"}. This record does not assert independent reproduction. ### LongReMix Accuracy (Sym. 20%): 96. Result ID: 69b0153b6dbb7075b95a17c7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Last"}. This record does not assert independent reproduction. ### CLIPCleaner Accuracy (Sym. 20%): 95.9. Result ID: 69b0153b6dbb7075b95a17cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Best"}. This record does not assert independent reproduction. ### DivideMix Accuracy (Sym. 20%): 95.7. Result ID: 69b0153b6dbb7075b95a17c5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Last"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.