# Image Classification on CIFAR-10 OOD DEEPNETS-1M (test) Source: [Image Classification on CIFAR-10 OOD DEEPNETS-1M (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:29.882Z Evaluation of Image Classification performance on the test split of the CIFAR-10 OOD DEEPNETS-1M dataset, focusing on accuracy across various model configurations (WIDE, DEEP, DENSE, BN-FREE, RESNET, VIT). 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 OOD DEEPNETS-1M (test) | | Metric | Accuracy (WIDE) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 (WIDE)](): Higher is better; unit: PERCENT. - [Accuracy (DEEP)](): Higher is better; unit: PERCENT. - [Accuracy (DENSE)](): Higher is better; unit: PERCENT. - [Accuracy (BN-FREE)](): Higher is better; unit: PERCENT. - [Accuracy (RESNET)](): Higher is better; unit: PERCENT. - [Accuracy (VIT)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (WIDE) | Result date | Report paper | | --- | --- | --- | --- | | SGD | 88.9 | Not recorded | 68fa6b1b1e209131cea2c408 | | Adam | 82 | Not recorded | 68fa6b1b1e209131cea2c408 | | SGD | 71.2 | Not recorded | 68fa6b1b1e209131cea2c408 | | GHN-2 | 64 | Not recorded | 68fa6b1b1e209131cea2c408 | | SGD | 47.2 | Not recorded | 68fa6b1b1e209131cea2c408 | | GHN-1 | 43.1 | Not recorded | 68fa6b1b1e209131cea2c408 | | MLP | 22.3 | Not recorded | 68fa6b1b1e209131cea2c408 | ### SGD Accuracy (WIDE): 88.9. Result ID: 698e5dbeffc3901de09cfb4c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#upd+":"25x10^3","training\_duration":"50 epochs"}. This record does not assert independent reproduction. ### Adam Accuracy (WIDE): 82. Result ID: 698e5dbeffc3901de09cfb4d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#upd+":"25x10^3","training\_duration":"50 epochs"}. This record does not assert independent reproduction. ### SGD Accuracy (WIDE): 71.2. Result ID: 698e5dbeffc3901de09cfb4b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#upd+":"2.5x10^3","training\_duration":"5 epochs"}. This record does not assert independent reproduction. ### GHN-2 Accuracy (WIDE): 64. Result ID: 698e5dbeffc3901de09cfb49. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"#upd+":"1"}. This record does not assert independent reproduction. ### SGD Accuracy (WIDE): 47.2. Result ID: 698e5dbeffc3901de09cfb4a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#upd+":"0.5x10^3","training\_duration":"1 epoch"}. This record does not assert independent reproduction. ### GHN-1 Accuracy (WIDE): 43.1. Result ID: 698e5dbeffc3901de09cfb48. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"#upd+":"1"}. This record does not assert independent reproduction. ### MLP Accuracy (WIDE): 22.3. Result ID: 698e5dbeffc3901de09cfb47. [Reporting paper]() Recorded evaluation configuration: {"#upd+":"1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.