# Image Classification on Spawrious many-to-many hard (test) Source: [Image Classification on Spawrious many-to-many hard (test)]() Collection index: [llms.txt]() Data updated: 2026-07-01T08:45:18.648Z Evaluation of Image Classification performance on the test split of the Spawrious dataset, specifically focusing on the Many-to-Many (M2M) Hard difficulty subset, reporting WGA and 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 many-to-many hard (test) | | Metric | WGA | | Unit | PERCENT | | 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 - [WGA](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | WGA | Result date | Report paper | | --- | --- | --- | --- | | CLIP | 79.9 | Not recorded | 6a449f0be0224bd4f4993061 | | QWEN3-VL | 73.8 | Not recorded | 6a449f0be0224bd4f4993061 | | Chang et al. | 66.7 | Not recorded | 6a449f0be0224bd4f4993061 | | AutoBackSwap | 64.3 | Not recorded | 6a449f0be0224bd4f4993061 | | SAM3 | 64 | Not recorded | 6a449f0be0224bd4f4993061 | | ERM | 51.3 | Not recorded | 6a449f0be0224bd4f4993061 | | CORAL | 49.8 | Not recorded | 6a449f0be0224bd4f4993061 | | Group DRO | 47.1 | Not recorded | 6a449f0be0224bd4f4993061 | | AFR | 41.3 | Not recorded | 6a449f0be0224bd4f4993061 | | DFR | 39.1 | Not recorded | 6a449f0be0224bd4f4993061 | | ERM | 19.6 | Not recorded | 6a449f0be0224bd4f4993061 | ### CLIP WGA: 79.9. Result ID: 6a44d39c73d097d845bfb575. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"zero-shot":"true"}. This record does not assert independent reproduction. ### QWEN3-VL WGA: 73.8. Result ID: 6a44d39c73d097d845bfb576. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"zero-shot":"true"}. This record does not assert independent reproduction. ### Chang et al. WGA: 66.7. Result ID: 6a44d39c73d097d845bfb572. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AutoBackSwap WGA: 64.3. Result ID: 6a44d39c73d097d845bfb573. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SAM3 WGA: 64. Result ID: 6a44d39c73d097d845bfb574. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"zero-shot":"true"}. This record does not assert independent reproduction. ### ERM WGA: 51.3. Result ID: 6a44d39c73d097d845bfb56c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CORAL WGA: 49.8. Result ID: 6a44d39c73d097d845bfb571. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Group DRO WGA: 47.1. Result ID: 6a44d39c73d097d845bfb570. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### AFR WGA: 41.3. Result ID: 6a44d39c73d097d845bfb56f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DFR WGA: 39.1. Result ID: 6a44d39c73d097d845bfb56e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ERM WGA: 19.6. Result ID: 6a44d39c73d097d845bfb56d. [Reporting paper]() Recorded evaluation configuration: {"augmentation":"heavy"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.