# Selective Classification on ImageNet V2 Original (test) Source: [Selective Classification on ImageNet V2 Original (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:52:38.844Z Evaluation of Selective Classification performance on the test split of the ImageNet V2 Original dataset. 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 | Selective Classification | | Dataset (including any stated split) | ImageNet V2 Original (test) | | Metric | Metric A | | Unit | SCALAR | | 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 - [Metric A](): Higher is better; unit: SCALAR. - [Metric N](): Higher is better; unit: SCALAR. ## Recorded results | Method | Metric A | Result date | Report paper | | --- | --- | --- | --- | | KNN | 30.4 | Not recorded | 68fa78a61e209131cea79954 | | MDS | 21.6 | Not recorded | 68fa78a61e209131cea79954 | | SIRC | 19.6 | Not recorded | 68fa78a61e209131cea79954 | | Energy | 17.6 | Not recorded | 68fa78a61e209131cea79954 | | Δ-KNN | 16.2 | Not recorded | 68fa78a61e209131cea79954 | | Δ-MDS | 13.7 | Not recorded | 68fa78a61e209131cea79954 | | MaxLogit | 13.5 | Not recorded | 68fa78a61e209131cea79954 | | MSP | 10.32 | Not recorded | 68fa78a61e209131cea79954 | | RLog | 9.14 | Not recorded | 68fa78a61e209131cea79954 | | Δ-KNN-RLog | 9.02 | Not recorded | 68fa78a61e209131cea79954 | | Δ-MDS-RLog | 8.86 | Not recorded | 68fa78a61e209131cea79954 | ### KNN Metric A: 30.4. Result ID: 699a67995698665ec4efe4be. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### MDS Metric A: 21.6. Result ID: 699a67995698665ec4efe4bd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### SIRC Metric A: 19.6. Result ID: 699a67995698665ec4efe4c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### Energy Metric A: 17.6. Result ID: 699a67995698665ec4efe4bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### Δ-KNN Metric A: 16.2. Result ID: 699a67995698665ec4efe4c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### Δ-MDS Metric A: 13.7. Result ID: 699a67995698665ec4efe4c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### MaxLogit Metric A: 13.5. Result ID: 699a67995698665ec4efe4bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### MSP Metric A: 10.32. Result ID: 699a67995698665ec4efe4ba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### RLog Metric A: 9.14. Result ID: 699a67995698665ec4efe4bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### Δ-KNN-RLog Metric A: 9.02. Result ID: 699a67995698665ec4efe4c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. ### Δ-MDS-RLog Metric A: 8.86. Result ID: 699a67995698665ec4efe4c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ResNet-50","Training Dataset":"ImageNet-1K","Pre-training Source":"Official PyTorch Repository"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.