# Image Classification on ImageNet (val) (Accuracy and Multi-Device Latency) Source: [Image Classification on ImageNet (val) (Accuracy and Multi-Device Latency)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:55.902Z Evaluation of Image Classification performance on the validation split of the ImageNet dataset, reporting Top-1 accuracy alongside inference latency measured across three distinct hardware configurations (Pixel 1, Pixel 2, Pixel 3). 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 (val) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 4 of 4 | | 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. - [Latency (Pixel 1)](): Lower is better; unit: TIME. - [Latency (Pixel 2)](): Lower is better; unit: TIME. - [Latency (Pixel 3)](): Lower is better; unit: TIME. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MobileNetV3-Large 1.0 | 73.8 | Not recorded | 68fa66ac1e209131cea11957 | | MobileNetV2 1.0 | 70.9 | Not recorded | 68fa66ac1e209131cea11957 | | MobileNetV3-Small | 64.9 | Not recorded | 68fa66ac1e209131cea11957 | | MobileNetV2 0.35 | 57.2 | Not recorded | 68fa66ac1e209131cea11957 | ### MobileNetV3-Large 1.0 Top-1 Accuracy: 73.8. Result ID: 698cffa78b517eb4331e4498. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Quantized":"true","Multiplier":"1.0"}. This record does not assert independent reproduction. ### MobileNetV2 1.0 Top-1 Accuracy: 70.9. Result ID: 698cffa78b517eb4331e4499. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Quantized":"true","Multiplier":"1.0"}. This record does not assert independent reproduction. ### MobileNetV3-Small Top-1 Accuracy: 64.9. Result ID: 698cffa78b517eb4331e449a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Quantized":"true"}. This record does not assert independent reproduction. ### MobileNetV2 0.35 Top-1 Accuracy: 57.2. Result ID: 698cffa78b517eb4331e449b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Quantized":"true","Multiplier":"0.35"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.