# Image Classification on ImageNet (Top-1 Accuracy, Throughput, and Speedup) Source: [Image Classification on ImageNet (Top-1 Accuracy, Throughput, and Speedup)]() Collection index: [llms.txt]() Data updated: 2026-05-20T07:13:33.632Z Evaluation of Image Classification performance on the standard ImageNet dataset, reporting Top-1 Accuracy alongside measured token throughput and estimated model speedup for 224x224 and 384x384 input resolutions. 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 | | Metric | Top-1 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. - [Throughput (Tokens/s) (224x224)](): Higher is better; unit: SCALAR. - [Throughput (Tokens/s) (384x384)](): Higher is better; unit: SCALAR. - [Speedup Factor (224x224)](): Higher is better; unit: SCALAR. - [Speedup Factor (384x384)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | DeiT | 79.8 | Not recorded | 6a0d4015f984739ed67377e9 | | S2S-Mamba | 79.3 | Not recorded | 6a0d4015f984739ed67377e9 | | A-ViT | 78.6 | Not recorded | 6a0d4015f984739ed67377e9 | | S2S-Mamba | 78.6 | Not recorded | 6a0d4015f984739ed67377e9 | | S2S-Mamba | 78.4 | Not recorded | 6a0d4015f984739ed67377e9 | | A-ViT | 78.2 | Not recorded | 6a0d4015f984739ed67377e9 | ### DeiT Top-1 Accuracy: 79.8. Result ID: 6a0d5e14fbc373592c04ee8c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Layers":"None","Retention Ratio (Ret.)":"1.00"}. This record does not assert independent reproduction. ### S2S-Mamba Top-1 Accuracy: 79.3. Result ID: 6a0d5e14fbc373592c04ee8f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Layers":"9–11","Retention Ratio (Ret.)":"1.00"}. This record does not assert independent reproduction. ### A-ViT Top-1 Accuracy: 78.6. Result ID: 6a0d5e14fbc373592c04ee8d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Layers":"None","Retention Ratio (Ret.)":"0.78"}. This record does not assert independent reproduction. ### S2S-Mamba Top-1 Accuracy: 78.6. Result ID: 6a0d5e14fbc373592c04ee90. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Layers":"9–11","Retention Ratio (Ret.)":"0.78"}. This record does not assert independent reproduction. ### S2S-Mamba Top-1 Accuracy: 78.4. Result ID: 6a0d5e14fbc373592c04ee91. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Layers":"9–11","Retention Ratio (Ret.)":"0.70"}. This record does not assert independent reproduction. ### A-ViT Top-1 Accuracy: 78.2. Result ID: 6a0d5e14fbc373592c04ee8e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Layers":"None","Retention Ratio (Ret.)":"0.70"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.