# Image Classification on ImageNet-C Average of 15 corruptions (test) Source: [Image Classification on ImageNet-C Average of 15 corruptions (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:40.156Z Evaluation of Image Classification performance on the ImageNet-C test set, specifically measuring accuracy across an average of 15 defined corruption types. 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-C Average of 15 corruptions (test) | | Metric | Top-1 Acc | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Acc | Result date | Report paper | | --- | --- | --- | --- | | RELICv2 | 44.8 | Not recorded | 68fa6dde1e209131cea3c8f8 | | RELIC | 44.5 | Not recorded | 68fa6dde1e209131cea3c8f8 | | BYOL | 42.8 | Not recorded | 68fa6dde1e209131cea3c8f8 | | Supervised | 40.9 | Not recorded | 68fa6dde1e209131cea3c8f8 | | SimCLR | 31.1 | Not recorded | 68fa6dde1e209131cea3c8f8 | ### RELICv2 Top-1 Acc: 44.8. Result ID: 698ff94d3a6c314849fd2bed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"Linear evaluation","Backbone":"ResNet-50","Pre-training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### RELIC Top-1 Acc: 44.5. Result ID: 698ff94d3a6c314849fd2bec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Protocol":"Linear evaluation","Backbone":"ResNet-50","Pre-training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### BYOL Top-1 Acc: 42.8. Result ID: 698ff94d3a6c314849fd2beb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"Linear evaluation","Backbone":"ResNet-50","Pre-training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### Supervised Top-1 Acc: 40.9. Result ID: 698ff94d3a6c314849fd2be9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"Linear evaluation","Backbone":"ResNet-50","Pre-training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. ### SimCLR Top-1 Acc: 31.1. Result ID: 698ff94d3a6c314849fd2bea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"Linear evaluation","Backbone":"ResNet-50","Pre-training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.