# Model Calibration on CIFAR-10, CIFAR-100, and SVHN Source: [Model Calibration on CIFAR-10, CIFAR-100, and SVHN]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:35:22.421Z Evaluation of model calibration performance across the CIFAR-10, CIFAR-100, and SVHN datasets, typically measured using Expected Calibration Error (ECE). 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 | Model Calibration | | Dataset (including any stated split) | CIFAR-10, CIFAR-100, and SVHN | | Metric | Average ECE | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 13 of 13 | | 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 - [Average ECE](): Lower is better; unit: SCALAR. ## Recorded results | Method | Average ECE | Result date | Report paper | | --- | --- | --- | --- | | BalCAL | 1.77 | Not recorded | 68fa780d1e209131cea768ef | | VTST | 3.11 | Not recorded | 68fa780d1e209131cea768ef | | TST | 3.23 | Not recorded | 68fa780d1e209131cea768ef | | Mixup | 3.61 | Not recorded | 68fa780d1e209131cea768ef | | LS | 4.2 | Not recorded | 68fa780d1e209131cea768ef | | MIT | 5.09 | Not recorded | 68fa780d1e209131cea768ef | | FLSD | 5.65 | Not recorded | 68fa780d1e209131cea768ef | | FL | 5.83 | Not recorded | 68fa780d1e209131cea768ef | | CPC | 6.81 | Not recorded | 68fa780d1e209131cea768ef | | ACLS | 7.18 | Not recorded | 68fa780d1e209131cea768ef | | PLP | 7.37 | Not recorded | 68fa780d1e209131cea768ef | | MMCE | 7.69 | Not recorded | 68fa780d1e209131cea768ef | | Vanilla | 10.44 | Not recorded | 68fa780d1e209131cea768ef | ### BalCAL Average ECE: 1.77. Result ID: 69957a703badfaffe6716b19. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### VTST Average ECE: 3.11. Result ID: 69957a703badfaffe6716b18. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### TST Average ECE: 3.23. Result ID: 69957a703badfaffe6716b17. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### Mixup Average ECE: 3.61. Result ID: 69957a703badfaffe6716b10. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### LS Average ECE: 4.2. Result ID: 69957a703badfaffe6716b0f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### MIT Average ECE: 5.09. Result ID: 69957a703badfaffe6716b11. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### FLSD Average ECE: 5.65. Result ID: 69957a703badfaffe6716b13. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### FL Average ECE: 5.83. Result ID: 69957a703badfaffe6716b12. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### CPC Average ECE: 6.81. Result ID: 69957a703badfaffe6716b14. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### ACLS Average ECE: 7.18. Result ID: 69957a703badfaffe6716b0e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### PLP Average ECE: 7.37. Result ID: 69957a703badfaffe6716b15. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### MMCE Average ECE: 7.69. Result ID: 69957a703badfaffe6716b16. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. ### Vanilla Average ECE: 10.44. Result ID: 69957a703badfaffe6716b0d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"WRN-28-10"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.