# Image Classification on ImageNet 1k (Top-1 Acc., Retention) Source: [Image Classification on ImageNet 1k (Top-1 Acc., Retention)]() Collection index: [llms.txt]() Data updated: 2026-04-02T09:17:19.214Z Evaluation of Image Classification performance on the ImageNet-1k dataset, reporting Top-1 Accuracy and Retention metrics. 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 | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. - [Retention](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | ConvNeXt-B | 85.51 | Not recorded | 68fa7a0b1e209131cea80c66 | | ConvNeXt-S | 84.57 | Not recorded | 68fa7a0b1e209131cea80c66 | | VBP | 83.4 | Not recorded | 68fa7a0b1e209131cea80c66 | | ConvNeXt-T | 82.9 | Not recorded | 68fa7a0b1e209131cea80c66 | | VBP | 82.82 | Not recorded | 68fa7a0b1e209131cea80c66 | | VBP | 81.3 | Not recorded | 68fa7a0b1e209131cea80c66 | | VBP | 57.1 | Not recorded | 68fa7a0b1e209131cea80c66 | | VBP | 30.92 | Not recorded | 68fa7a0b1e209131cea80c66 | | VBP | 16.8 | Not recorded | 68fa7a0b1e209131cea80c66 | ### ConvNeXt-B Top-1 Accuracy: 85.51. Result ID: 69ce341c47f34ce924b79c93. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ConvNeXt-B","Method (Full vs VBP)":"Full","MACs (G)":"15.38","Parameters (M)":"88.59"}. This record does not assert independent reproduction. ### ConvNeXt-S Top-1 Accuracy: 84.57. Result ID: 69ce341c47f34ce924b79c90. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ConvNeXt-S","Method (Full vs VBP)":"Full","MACs (G)":"8.71","Parameters (M)":"50.22"}. This record does not assert independent reproduction. ### VBP Top-1 Accuracy: 83.4. Result ID: 69ce341c47f34ce924b79c95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ConvNeXt-B","Method (Full vs VBP)":"VBP","MACs (G)":"8.91 (-42.1%)","Parameters (M)":"41.32 (-53.4%)","Pruning Rate":"50%","Evaluation Condition":"VBP (Final)"}. This record does not assert independent reproduction. ### ConvNeXt-T Top-1 Accuracy: 82.9. Result ID: 69ce341c47f34ce924b79c8d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"ConvNeXt-T","Method (Full vs VBP)":"Full","MACs (G)":"4.47","Parameters (M)":"28.59"}. This record does not assert independent reproduction. ### VBP Top-1 Accuracy: 82.82. Result ID: 69ce341c47f34ce924b79c92. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ConvNeXt-S","Method (Full vs VBP)":"VBP","MACs (G)":"5.11 (-41.3%)","Parameters (M)":"23.50 (-53.2%)","Pruning Rate":"50%","Evaluation Condition":"VBP (Final)"}. This record does not assert independent reproduction. ### VBP Top-1 Accuracy: 81.3. Result ID: 69ce341c47f34ce924b79c8f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ConvNeXt-T","Method (Full vs VBP)":"VBP","MACs (G)":"2.96 (-33.8%)","Parameters (M)":"12.61 (-55.9%)","Pruning Rate":"50%","Evaluation Condition":"VBP (Final)"}. This record does not assert independent reproduction. ### VBP Top-1 Accuracy: 57.1. Result ID: 69ce341c47f34ce924b79c94. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ConvNeXt-B","Method (Full vs VBP)":"VBP","MACs (G)":"8.91 (-42.1%)","Parameters (M)":"41.32 (-53.4%)","Pruning Rate":"50%","Evaluation Condition":"Retention (Pre-finetuning)"}. This record does not assert independent reproduction. ### VBP Top-1 Accuracy: 30.92. Result ID: 69ce341c47f34ce924b79c91. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ConvNeXt-S","Method (Full vs VBP)":"VBP","MACs (G)":"5.11 (-41.3%)","Parameters (M)":"23.50 (-53.2%)","Pruning Rate":"50%","Evaluation Condition":"Retention (Pre-finetuning)"}. This record does not assert independent reproduction. ### VBP Top-1 Accuracy: 16.8. Result ID: 69ce341c47f34ce924b79c8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ConvNeXt-T","Method (Full vs VBP)":"VBP","MACs (G)":"2.96 (-33.8%)","Parameters (M)":"12.61 (-55.9%)","Pruning Rate":"50%","Evaluation Condition":"Retention (Pre-finetuning)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.