# Image Classification on CIFAR10 PACS (combined) Source: [Image Classification on CIFAR10 PACS (combined)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:28.902Z Evaluation of Image Classification performance on the combined CIFAR-10 PACS 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 | Image Classification | | Dataset (including any stated split) | CIFAR10 PACS (combined) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Test-Time Dynamic Model Selection (MetaCLIP-SigLIP) | 99 | Not recorded | 693ba1676cfd488761a55055 | | Best individual VLM (MetaCLIP-SigLIP) | 98.7 | Not recorded | 693ba1676cfd488761a55055 | | Best individual VLM (MetaCLIP-SigLIP) | 98.7 | Not recorded | 693ba1676cfd488761a55055 | | Test-Time Dynamic Model Selection (MetaCLIP-SigLIP) | 98.6 | Not recorded | 693ba1676cfd488761a55055 | | Test-Time Dynamic Model Selection (MetaCLIP-SigLIP) | 98.5 | Not recorded | 693ba1676cfd488761a55055 | | Best individual VLM (MetaCLIP-SigLIP) | 98.4 | Not recorded | 693ba1676cfd488761a55055 | | Test-Time Dynamic Model Selection (CLIP-ALIGN) | 96.2 | Not recorded | 693ba1676cfd488761a55055 | | Test-Time Dynamic Model Selection (CLIP-ALIGN) | 96 | Not recorded | 693ba1676cfd488761a55055 | | Test-Time Dynamic Model Selection (CLIP-ALIGN) | 95.8 | Not recorded | 693ba1676cfd488761a55055 | | Best individual VLM (CLIP-ALIGN) | 94.8 | Not recorded | 693ba1676cfd488761a55055 | | Best individual VLM (CLIP-ALIGN) | 94.8 | Not recorded | 693ba1676cfd488761a55055 | | Best individual VLM (CLIP-ALIGN) | 94.2 | Not recorded | 693ba1676cfd488761a55055 | ### Test-Time Dynamic Model Selection (MetaCLIP-SigLIP) Accuracy: 99. Result ID: 699971385698665ec4df5e1f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Pair":"MetaCLIP-SigLIP","Number of trials":"1500 trials"}. This record does not assert independent reproduction. ### Best individual VLM (MetaCLIP-SigLIP) Accuracy: 98.7. Result ID: 699971385698665ec4df5e1e. [Reporting paper]() Recorded evaluation configuration: {"Model Pair":"MetaCLIP-SigLIP","Number of trials":"1500 trials"}. This record does not assert independent reproduction. ### Best individual VLM (MetaCLIP-SigLIP) Accuracy: 98.7. Result ID: 699971385698665ec4df5e20. [Reporting paper]() Recorded evaluation configuration: {"Model Pair":"MetaCLIP-SigLIP","Number of trials":"2500 trials"}. This record does not assert independent reproduction. ### Test-Time Dynamic Model Selection (MetaCLIP-SigLIP) Accuracy: 98.6. Result ID: 699971385698665ec4df5e21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Pair":"MetaCLIP-SigLIP","Number of trials":"2500 trials"}. This record does not assert independent reproduction. ### Test-Time Dynamic Model Selection (MetaCLIP-SigLIP) Accuracy: 98.5. Result ID: 699971385698665ec4df5e23. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Pair":"MetaCLIP-SigLIP","Number of trials":"4000 trials"}. This record does not assert independent reproduction. ### Best individual VLM (MetaCLIP-SigLIP) Accuracy: 98.4. Result ID: 699971385698665ec4df5e22. [Reporting paper]() Recorded evaluation configuration: {"Model Pair":"MetaCLIP-SigLIP","Number of trials":"4000 trials"}. This record does not assert independent reproduction. ### Test-Time Dynamic Model Selection (CLIP-ALIGN) Accuracy: 96.2. Result ID: 699971385698665ec4df5e27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Pair":"CLIP-ALIGN","Number of trials":"2500 trials"}. This record does not assert independent reproduction. ### Test-Time Dynamic Model Selection (CLIP-ALIGN) Accuracy: 96. Result ID: 699971385698665ec4df5e25. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Pair":"CLIP-ALIGN","Number of trials":"1500 trials"}. This record does not assert independent reproduction. ### Test-Time Dynamic Model Selection (CLIP-ALIGN) Accuracy: 95.8. Result ID: 699971385698665ec4df5e29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Pair":"CLIP-ALIGN","Number of trials":"4000 trials"}. This record does not assert independent reproduction. ### Best individual VLM (CLIP-ALIGN) Accuracy: 94.8. Result ID: 699971385698665ec4df5e26. [Reporting paper]() Recorded evaluation configuration: {"Model Pair":"CLIP-ALIGN","Number of trials":"2500 trials"}. This record does not assert independent reproduction. ### Best individual VLM (CLIP-ALIGN) Accuracy: 94.8. Result ID: 699971385698665ec4df5e28. [Reporting paper]() Recorded evaluation configuration: {"Model Pair":"CLIP-ALIGN","Number of trials":"4000 trials"}. This record does not assert independent reproduction. ### Best individual VLM (CLIP-ALIGN) Accuracy: 94.2. Result ID: 699971385698665ec4df5e24. [Reporting paper]() Recorded evaluation configuration: {"Model Pair":"CLIP-ALIGN","Number of trials":"1500 trials"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.