# Image Classification on ImageNet-1K and Variants (V2, A, R, O, Sketch) 1.0 (test) Source: [Image Classification on ImageNet-1K and Variants (V2, A, R, O, Sketch) 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:47:01.785Z Comprehensive evaluation of Image Classification performance across the base ImageNet-1K test set and its five major Out-of-Distribution variants: V2, A, R, O, and Sketch, reporting individual scores and averages. 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-1K and Variants (V2, A, R, O, Sketch) 1.0 (test) | | Metric | ImageNet-1K Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [ImageNet-1K Accuracy](): Higher is better; unit: PERCENT. - [Top-1 Accuracy](): Higher is better; unit: PERCENT. - [ImageNet-V2 Accuracy](): Higher is better; unit: PERCENT. - [ImageNet-A Accuracy](): Higher is better; unit: PERCENT. - [ImageNet-R Accuracy](): Higher is better; unit: PERCENT. - [ImageNet-O Accuracy](): Higher is better; unit: PERCENT. - [ImageNet-Sketch Accuracy](): Higher is better; unit: PERCENT. - [Overall Average Accuracy](): Higher is better; unit: PERCENT. - [In-Distribution Average Accuracy](): Higher is better; unit: PERCENT. - [Out-of-Distribution Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | ImageNet-1K Accuracy | Result date | Report paper | | --- | --- | --- | --- | | CLIP-PGS0.3 | 38.6 | Not recorded | 68fa77961e209131cea742b2 | | CLIP-PGS0.5 | 38 | Not recorded | 68fa77961e209131cea742b2 | | E-CLIP | 36.3 | Not recorded | 68fa77961e209131cea742b2 | | CLIP | 36.1 | Not recorded | 68fa77961e209131cea742b2 | | A-CLIP | 35.2 | Not recorded | 68fa77961e209131cea742b2 | | FLIP | 34.4 | Not recorded | 68fa77961e209131cea742b2 | ### CLIP-PGS0.3 ImageNet-1K Accuracy: 38.6. Result ID: 6995483b3badfaffe63712ea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"protocol":"zero-shot"}. This record does not assert independent reproduction. ### CLIP-PGS0.5 ImageNet-1K Accuracy: 38. Result ID: 6995483b3badfaffe63712e9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"protocol":"zero-shot"}. This record does not assert independent reproduction. ### E-CLIP ImageNet-1K Accuracy: 36.3. Result ID: 6995483b3badfaffe63712e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"protocol":"zero-shot"}. This record does not assert independent reproduction. ### CLIP ImageNet-1K Accuracy: 36.1. Result ID: 6995483b3badfaffe63712e5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"protocol":"zero-shot"}. This record does not assert independent reproduction. ### A-CLIP ImageNet-1K Accuracy: 35.2. Result ID: 6995483b3badfaffe63712e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"protocol":"zero-shot"}. This record does not assert independent reproduction. ### FLIP ImageNet-1K Accuracy: 34.4. Result ID: 6995483b3badfaffe63712e6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"protocol":"zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.