# Image Classification on CIFAR-100 200 labels Source: [Image Classification on CIFAR-100 200 labels]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:07:19.440Z Evaluation of Image Classification performance on the CIFAR-100 dataset restricted to 200 labeled examples. 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) | CIFAR-100 200 labels | | Metric | Top-1 Error Rate | | Unit | PERCENT | | Direction | Lower 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 - [Top-1 Error Rate](): Lower is better; unit: PERCENT. - [Average Gain](): Higher is better; unit: SCALAR. ## Recorded results | Method | Top-1 Error Rate | Result date | Report paper | | --- | --- | --- | --- | | SoftMatch/FreeMatch + SemiReward | 20.06 | Not recorded | 68fa72451e209131cea556d1 | | SoftMatch/FreeMatch | 21.07 | Not recorded | 68fa72451e209131cea556d1 | | FlexMatch + SemiReward | 23.74 | Not recorded | 68fa72451e209131cea556d1 | | FlexMatch | 25.72 | Not recorded | 68fa72451e209131cea556d1 | | Pseudo Label + SemiReward | 31.94 | Not recorded | 68fa72451e209131cea556d1 | | Pseudo Label | 32.78 | Not recorded | 68fa72451e209131cea556d1 | ### SoftMatch/FreeMatch + SemiReward Top-1 Error Rate: 20.06. Result ID: 699229363a6c3148490cff83. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT \[Dosovitskiy et al., 2021\] / ResNet-50 \[He et al., 2016\]","SemiReward":true}. This record does not assert independent reproduction. ### SoftMatch/FreeMatch Top-1 Error Rate: 21.07. Result ID: 699229363a6c3148490cff82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT \[Dosovitskiy et al., 2021\] / ResNet-50 \[He et al., 2016\]","SemiReward":false}. This record does not assert independent reproduction. ### FlexMatch + SemiReward Top-1 Error Rate: 23.74. Result ID: 699229363a6c3148490cff81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT \[Dosovitskiy et al., 2021\] / ResNet-50 \[He et al., 2016\]","SemiReward":true}. This record does not assert independent reproduction. ### FlexMatch Top-1 Error Rate: 25.72. Result ID: 699229363a6c3148490cff80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT \[Dosovitskiy et al., 2021\] / ResNet-50 \[He et al., 2016\]","SemiReward":false}. This record does not assert independent reproduction. ### Pseudo Label + SemiReward Top-1 Error Rate: 31.94. Result ID: 699229363a6c3148490cff7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT \[Dosovitskiy et al., 2021\] / ResNet-50 \[He et al., 2016\]","SemiReward":true}. This record does not assert independent reproduction. ### Pseudo Label Top-1 Error Rate: 32.78. Result ID: 699229363a6c3148490cff7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT \[Dosovitskiy et al., 2021\] / ResNet-50 \[He et al., 2016\]","SemiReward":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.