# Image Classification on ImageNet-1k (val) (T1/T5 Threshold Accuracy and AuC) Source: [Image Classification on ImageNet-1k (val) (T1/T5 Threshold Accuracy and AuC)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:16.390Z Evaluation of Image Classification performance on the validation split of ImageNet-1K, reporting Top-1 and Top-5 accuracy across various thresholds (0%, 30%, 50%, 78%) and Area Under Curve (AuC). 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 Accuracy @ 0% Threshold | | 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 Accuracy @ 0% Threshold](): Higher is better; unit: PERCENT. - [Top-5 Accuracy @ 0% Threshold](): Higher is better; unit: PERCENT. - [Top-1 Accuracy @ 30% Threshold](): Higher is better; unit: PERCENT. - [Top-5 Accuracy @ 30% Threshold](): Higher is better; unit: PERCENT. - [Top-1 Accuracy @ 50% Threshold](): Higher is better; unit: PERCENT. - [Top-5 Accuracy @ 50% Threshold](): Higher is better; unit: PERCENT. - [Top-1 Accuracy @ 78% Threshold](): Higher is better; unit: PERCENT. - [Top-5 Accuracy @ 78% Threshold](): Higher is better; unit: PERCENT. - [Area Under Curve (AuC)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy @ 0% Threshold | Result date | Report paper | | --- | --- | --- | --- | | CViT | 83.11 | Not recorded | 692d2113d6b0dd33429316ba | | RViT | 83.1 | Not recorded | 692d2113d6b0dd33429316ba | | ViT | 82.91 | Not recorded | 692d2113d6b0dd33429316ba | | ViT+C | 82.84 | Not recorded | 692d2113d6b0dd33429316ba | | DynamicViT | 81.74 | Not recorded | 692d2113d6b0dd33429316ba | ### CViT Top-1 Accuracy @ 0% Threshold: 83.11. Result ID: 6995e4273badfaffe6ebf6ff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Mask":"Collapse order"}. This record does not assert independent reproduction. ### RViT Top-1 Accuracy @ 0% Threshold: 83.1. Result ID: 6995e4273badfaffe6ebf6fe. [Reporting paper]() Recorded evaluation configuration: {"Training Mask":"Random"}. This record does not assert independent reproduction. ### ViT Top-1 Accuracy @ 0% Threshold: 82.91. Result ID: 6995e4273badfaffe6ebf6fb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Masking":"Random during inference"}. This record does not assert independent reproduction. ### ViT+C Top-1 Accuracy @ 0% Threshold: 82.84. Result ID: 6995e4273badfaffe6ebf6fd. [Reporting paper]() Recorded evaluation configuration: {"Masking":"Collapse masks","Training":"Randomly masked"}. This record does not assert independent reproduction. ### DynamicViT Top-1 Accuracy @ 0% Threshold: 81.74. Result ID: 6995e4273badfaffe6ebf6fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeiT-B","Type":"Token-pruning"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.