# Image Classification on ImageNet-C Overall Average (7x5 Severities) Source: [Image Classification on ImageNet-C Overall Average (7x5 Severities)]() Collection index: [llms.txt]() Data updated: 2026-03-19T09:09:06.363Z Evaluation of Image Classification performance on the ImageNet-C dataset, reporting the overall average metric calculated across 7 corruption types evaluated at 5 severity levels. 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 overall (mean over 7 corruptions x 5 severities) | | 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. - [NLL (Cross-Entropy)](): Lower is better; unit: SCALAR. - [ECE](): Lower is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | DropBlock | 39 | Not recorded | 69bb831d0636e5bf4afc1aea | | IID Gaussian | 38.8 | Not recorded | 69bb831d0636e5bf4afc1aea | | Corr. Gaussian | 38.6 | Not recorded | 69bb831d0636e5bf4afc1aea | | Dropout | 38.4 | Not recorded | 69bb831d0636e5bf4afc1aea | | GCh | 38.3 | Not recorded | 69bb831d0636e5bf4afc1aea | | None | 38.2 | Not recorded | 69bb831d0636e5bf4afc1aea | ### DropBlock Top-1 Accuracy: 39. Result ID: 69bbbd2d47f34ce924a5cecc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"g":"0.1","Injection Stage":"late-stage"}. This record does not assert independent reproduction. ### IID Gaussian Top-1 Accuracy: 38.8. Result ID: 69bbbd2d47f34ce924a5cecd. [Reporting paper]() Recorded evaluation configuration: {"g":"0.1","Injection Stage":"late-stage"}. This record does not assert independent reproduction. ### Corr. Gaussian Top-1 Accuracy: 38.6. Result ID: 69bbbd2d47f34ce924a5cece. [Reporting paper]() Recorded evaluation configuration: {"g":"0.1","Injection Stage":"late-stage"}. This record does not assert independent reproduction. ### Dropout Top-1 Accuracy: 38.4. Result ID: 69bbbd2d47f34ce924a5cecb. [Reporting paper]() Recorded evaluation configuration: {"g":"0.1","Injection Stage":"late-stage"}. This record does not assert independent reproduction. ### GCh Top-1 Accuracy: 38.3. Result ID: 69bbbd2d47f34ce924a5cecf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"g":"0.1","Injection Stage":"late-stage"}. This record does not assert independent reproduction. ### None Top-1 Accuracy: 38.2. Result ID: 69bbbd2d47f34ce924a5ceca. [Reporting paper]() Recorded evaluation configuration: {"g":"0","Injection Stage":"late-stage"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.