# Image Classification on Spawrious M2M-Hard (test) Source: [Image Classification on Spawrious M2M-Hard (test)]() Collection index: [llms.txt]() Data updated: 2026-06-04T08:08:34.208Z Evaluation of Image Classification performance on the test split of the Spawrious M2M-Hard subset, reporting Worst-Group Accuracy. 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) | Spawrious M2M-Hard (test) | | Metric | Worst-Group 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 - [Worst-Group Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Worst-Group Accuracy | Result date | Report paper | | --- | --- | --- | --- | | DFR | 73.9 | Not recorded | 6a21065cc10484bac23efe91 | | DFR | 72.3 | Not recorded | 6a21065cc10484bac23efe91 | | DFR | 69.7 | Not recorded | 6a21065cc10484bac23efe91 | | DFR + A^2 | 64.6 | Not recorded | 6a21065cc10484bac23efe91 | | A^2\_LR cross-model | 64.6 | Not recorded | 6a21065cc10484bac23efe91 | | DFR | 49.9 | Not recorded | 6a21065cc10484bac23efe91 | ### DFR Worst-Group Accuracy: 73.9. Result ID: 6a213221fbc373592c1c9cf6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Configuration":"DFR","Backbone":"ViT-G (1.1B)"}. This record does not assert independent reproduction. ### DFR Worst-Group Accuracy: 72.3. Result ID: 6a213221fbc373592c1c9cf5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Configuration":"DFR","Backbone":"ViT-L (300M)"}. This record does not assert independent reproduction. ### DFR Worst-Group Accuracy: 69.7. Result ID: 6a213221fbc373592c1c9cf4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Configuration":"DFR","Backbone":"ViT-B (86M)"}. This record does not assert independent reproduction. ### DFR + A^2 Worst-Group Accuracy: 64.6. Result ID: 6a213221fbc373592c1c9cf3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Configuration":"DFR + A^2","Backbone":"ViT-S (21M)"}. This record does not assert independent reproduction. ### A^2\_LR cross-model Worst-Group Accuracy: 64.6. Result ID: 6a213221fbc373592c1c9cf7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Configuration":"A^2\_LR cross-model","Backbone":"ViT-S × ViT-G"}. This record does not assert independent reproduction. ### DFR Worst-Group Accuracy: 49.9. Result ID: 6a213221fbc373592c1c9cf2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Configuration":"DFR","Backbone":"ViT-S (21M)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.