# Image Classification on ImageNet 1K (val) (Top-1 Accuracy at 100 & 200 eps) Source: [Image Classification on ImageNet 1K (val) (Top-1 Accuracy at 100 & 200 eps)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:52.713Z Evaluation of Image Classification performance on the validation split of ImageNet 1K, specifically reporting Top-1 accuracy measured under 100 and 200 epsilon conditions. 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 (val) | | Metric | Top-1 Acc (100 eps) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 Acc (100 eps)](): Higher is better; unit: PERCENT. - [Top-1 Acc (200 eps)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Acc (100 eps) | Result date | Report paper | | --- | --- | --- | --- | | CW-RGP 4 | 69.7 | Not recorded | 68fa6d9d1e209131cea3ad4b | | W-MSE 4 | 69.4 | Not recorded | 68fa6d9d1e209131cea3ad4b | | Zero-CL | 68.9 | Not recorded | 68fa6d9d1e209131cea3ad4b | | SimSiam | 68.1 | Not recorded | 68fa6d9d1e209131cea3ad4b | | MoCo v2 | 67.4 | Not recorded | 68fa6d9d1e209131cea3ad4b | | W-MSE 4 (repro.) | 66.7 | Not recorded | 68fa6d9d1e209131cea3ad4b | | SimCLR | 66.5 | Not recorded | 68fa6d9d1e209131cea3ad4b | | BYOL | 66.5 | Not recorded | 68fa6d9d1e209131cea3ad4b | | SwAV | 66.5 | Not recorded | 68fa6d9d1e209131cea3ad4b | | BYOL (repro.) | 66.1 | Not recorded | 68fa6d9d1e209131cea3ad4b | | SwAV (repro.) | 65.8 | Not recorded | 68fa6d9d1e209131cea3ad4b | ### CW-RGP 4 Top-1 Acc (100 eps): 69.7. Result ID: 698fc4993a6c314849fbb513. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Batch size":"512","Encoder":"ResNet-50","Evaluation Protocol":"linear classification"}. This record does not assert independent reproduction. ### W-MSE 4 Top-1 Acc (100 eps): 69.4. Result ID: 698fc4993a6c314849fbb50e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Batch size":"4096","Encoder":"ResNet-50","Evaluation Protocol":"linear classification"}. This record does not assert independent reproduction. ### Zero-CL Top-1 Acc (100 eps): 68.9. Result ID: 698fc4993a6c314849fbb50f. [Reporting paper]() Recorded evaluation configuration: {"Batch size":"1024","Encoder":"ResNet-50","Evaluation Protocol":"linear classification"}. This record does not assert independent reproduction. ### SimSiam Top-1 Acc (100 eps): 68.1. Result ID: 698fc4993a6c314849fbb50d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Batch size":"256","Encoder":"ResNet-50","Evaluation Protocol":"linear classification"}. This record does not assert independent reproduction. ### MoCo v2 Top-1 Acc (100 eps): 67.4. Result ID: 698fc4993a6c314849fbb50a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Batch size":"256","Encoder":"ResNet-50","Evaluation Protocol":"linear classification"}. This record does not assert independent reproduction. ### W-MSE 4 (repro.) Top-1 Acc (100 eps): 66.7. Result ID: 698fc4993a6c314849fbb512. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Batch size":"512","Encoder":"ResNet-50","Evaluation Protocol":"linear classification"}. This record does not assert independent reproduction. ### SimCLR Top-1 Acc (100 eps): 66.5. Result ID: 698fc4993a6c314849fbb509. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Batch size":"4096","Encoder":"ResNet-50","Evaluation Protocol":"linear classification"}. This record does not assert independent reproduction. ### BYOL Top-1 Acc (100 eps): 66.5. Result ID: 698fc4993a6c314849fbb50b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Batch size":"4096","Encoder":"ResNet-50","Evaluation Protocol":"linear classification"}. This record does not assert independent reproduction. ### SwAV Top-1 Acc (100 eps): 66.5. Result ID: 698fc4993a6c314849fbb50c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Batch size":"4096","Encoder":"ResNet-50","Evaluation Protocol":"linear classification"}. This record does not assert independent reproduction. ### BYOL (repro.) Top-1 Acc (100 eps): 66.1. Result ID: 698fc4993a6c314849fbb510. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Batch size":"512","Encoder":"ResNet-50","Evaluation Protocol":"linear classification"}. This record does not assert independent reproduction. ### SwAV (repro.) Top-1 Acc (100 eps): 65.8. Result ID: 698fc4993a6c314849fbb511. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Batch size":"512","Encoder":"ResNet-50","Evaluation Protocol":"linear classification"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.