# Image Classification on ImageNet-R (20 tasks) Source: [Image Classification on ImageNet-R (20 tasks)]() Collection index: [llms.txt]() Data updated: 2026-05-12T07:50:25.256Z Evaluation of Image Classification performance on the ImageNet-R 20 tasks variant, reporting standard Accuracy. 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) | ImageNet-R (20 tasks) | | Metric | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | TRM | 89.9 | Not recorded | 6a02b3f7dbc836b87d82458d | | MagMAX | 89.1 | Not recorded | 6a02b3f7dbc836b87d82458d | | BECAME | 87.1 | Not recorded | 6a02b3f7dbc836b87d82458d | | TIES | 86.9 | Not recorded | 6a02b3f7dbc836b87d82458d | | Model Stock | 86.7 | Not recorded | 6a02b3f7dbc836b87d82458d | | TRM | 82.5 | Not recorded | 6a02b3f7dbc836b87d82458d | | MagMAX | 79.2 | Not recorded | 6a02b3f7dbc836b87d82458d | | TIES | 78.4 | Not recorded | 6a02b3f7dbc836b87d82458d | | Model Stock | 76.4 | Not recorded | 6a02b3f7dbc836b87d82458d | | BECAME | 76.1 | Not recorded | 6a02b3f7dbc836b87d82458d | ### TRM Accuracy: 89.9. Result ID: 6a02db3b47f34ce924e5612b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-L/14","Pre-training":"WebImageText"}. This record does not assert independent reproduction. ### MagMAX Accuracy: 89.1. Result ID: 6a02db3b47f34ce924e56129. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-L/14","Pre-training":"WebImageText"}. This record does not assert independent reproduction. ### BECAME Accuracy: 87.1. Result ID: 6a02db3b47f34ce924e5612a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-L/14","Pre-training":"WebImageText"}. This record does not assert independent reproduction. ### TIES Accuracy: 86.9. Result ID: 6a02db3b47f34ce924e56128. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-L/14","Pre-training":"WebImageText"}. This record does not assert independent reproduction. ### Model Stock Accuracy: 86.7. Result ID: 6a02db3b47f34ce924e56127. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-L/14","Pre-training":"WebImageText"}. This record does not assert independent reproduction. ### TRM Accuracy: 82.5. Result ID: 6a02db3b47f34ce924e5613a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pre-trained dataset":"LAION-400M"}. This record does not assert independent reproduction. ### MagMAX Accuracy: 79.2. Result ID: 6a02db3b47f34ce924e56138. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pre-trained dataset":"LAION-400M"}. This record does not assert independent reproduction. ### TIES Accuracy: 78.4. Result ID: 6a02db3b47f34ce924e56137. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pre-trained dataset":"LAION-400M"}. This record does not assert independent reproduction. ### Model Stock Accuracy: 76.4. Result ID: 6a02db3b47f34ce924e56136. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pre-trained dataset":"LAION-400M"}. This record does not assert independent reproduction. ### BECAME Accuracy: 76.1. Result ID: 6a02db3b47f34ce924e56139. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pre-trained dataset":"LAION-400M"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.