# Zero-shot classification on ImageNet & Variants (test) Source: [Zero-shot classification on ImageNet & Variants (test)]() Collection index: [llms.txt]() Data updated: 2026-03-05T08:38:20.200Z Evaluation of Zero-shot Classification performance on the test split of the combined ImageNet and its variants datasets. 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 | Zero-shot classification | | Dataset (including any stated split) | ImageNet & Variants (test) | | Metric | Zero-shot Accuracy (ImageNet & Variants) | | 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 - [Zero-shot Accuracy (ImageNet & Variants)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Zero-shot Accuracy (ImageNet & Variants) | Result date | Report paper | | --- | --- | --- | --- | | NeuCLIP | 58.69 | Not recorded | 6914148c2828b7cc6937eba9 | | FastCLIP | 57.87 | Not recorded | 6914148c2828b7cc6937eba9 | | OpenCLIP | 57.49 | Not recorded | 6914148c2828b7cc6937eba9 | | SigLIP | 57.2 | Not recorded | 6914148c2828b7cc6937eba9 | | AmorLIP | 57.12 | Not recorded | 6914148c2828b7cc6937eba9 | | NeuCLIP | 55.88 | Not recorded | 6914148c2828b7cc6937eba9 | | FastCLIP | 55.44 | Not recorded | 6914148c2828b7cc6937eba9 | | OpenCLIP | 55.16 | Not recorded | 6914148c2828b7cc6937eba9 | | SigLIP | 55.09 | Not recorded | 6914148c2828b7cc6937eba9 | | AmorLIP | 55.09 | Not recorded | 6914148c2828b7cc6937eba9 | ### NeuCLIP Zero-shot Accuracy (ImageNet & Variants): 58.69. Result ID: 69a940e96dbb7075b952bbc1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"DFN-1B"}. This record does not assert independent reproduction. ### FastCLIP Zero-shot Accuracy (ImageNet & Variants): 57.87. Result ID: 69a940e96dbb7075b952bbbe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"DFN-1B"}. This record does not assert independent reproduction. ### OpenCLIP Zero-shot Accuracy (ImageNet & Variants): 57.49. Result ID: 69a940e96dbb7075b952bbbd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"DFN-1B"}. This record does not assert independent reproduction. ### SigLIP Zero-shot Accuracy (ImageNet & Variants): 57.2. Result ID: 69a940e96dbb7075b952bbbf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"DFN-1B"}. This record does not assert independent reproduction. ### AmorLIP Zero-shot Accuracy (ImageNet & Variants): 57.12. Result ID: 69a940e96dbb7075b952bbc0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"DFN-1B"}. This record does not assert independent reproduction. ### NeuCLIP Zero-shot Accuracy (ImageNet & Variants): 55.88. Result ID: 69a940e96dbb7075b952bbe9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"DFN-192M"}. This record does not assert independent reproduction. ### FastCLIP Zero-shot Accuracy (ImageNet & Variants): 55.44. Result ID: 69a940e96dbb7075b952bbe6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"DFN-192M"}. This record does not assert independent reproduction. ### OpenCLIP Zero-shot Accuracy (ImageNet & Variants): 55.16. Result ID: 69a940e96dbb7075b952bbe5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Dataset":"DFN-192M"}. This record does not assert independent reproduction. ### SigLIP Zero-shot Accuracy (ImageNet & Variants): 55.09. Result ID: 69a940e96dbb7075b952bbe7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"DFN-192M"}. This record does not assert independent reproduction. ### AmorLIP Zero-shot Accuracy (ImageNet & Variants): 55.09. Result ID: 69a940e96dbb7075b952bbe8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Dataset":"DFN-192M"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.