# Ablation Study (Encoders/Classifiers) on CIFAR-100 (test)

Source: [Ablation Study (Encoders/Classifiers) on CIFAR-100 (test)](<https://www.sota2.com/research/sota/ablation-study-encoders-classifiers-on-cifar-100-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:53:16.779Z

Evaluation of model component performance (Encoders/Classifiers) on the CIFAR-100 test set, typically measured using Negative Log-Likelihood (NLL).

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 | Ablation Study (Encoders/Classifiers) |
| Dataset (including any stated split) | CIFAR-100 (test) |
| Metric | NLL |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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

- [NLL](<https://www.sota2.com/research/sota/ablation-study-encoders-classifiers-on-cifar-100-test.md?metric=NLL>): Lower is better; unit: SCALAR.

## Recorded results

| Method | NLL | Result date | Report paper |
| --- | --- | --- | --- |
| MixMo (Final) | 0.563 | Not recorded | 68fa6a9a1e209131cea294dd |
| MixMo (Variant - Predict Predominant) | 0.598 | Not recorded | 68fa6a9a1e209131cea294dd |
| MixMo (Baseline) | 0.604 | Not recorded | 68fa6a9a1e209131cea294dd |
| MixMo (Variant) | 0.666 | Not recorded | 68fa6a9a1e209131cea294dd |
| MixMo (Variant - Random Match) | 0.687 | Not recorded | 68fa6a9a1e209131cea294dd |

### MixMo (Final)

NLL: 0.563. Result ID: 699ac8335698665ec4569e86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294dd.md>)

Recorded evaluation configuration: {"#Enc":2,"#Clas":2}. This record does not assert independent reproduction.

### MixMo (Variant - Predict Predominant)

NLL: 0.598. Result ID: 699ac8335698665ec4569e85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294dd.md>)

Recorded evaluation configuration: {"#Enc":1,"#Clas":2,"variant":"predominant input targeting"}. This record does not assert independent reproduction.

### MixMo (Baseline)

NLL: 0.604. Result ID: 699ac8335698665ec4569e82.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294dd.md>)

Recorded evaluation configuration: {"#Enc":1,"#Clas":1}. This record does not assert independent reproduction.

### MixMo (Variant)

NLL: 0.666. Result ID: 699ac8335698665ec4569e83.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294dd.md>)

Recorded evaluation configuration: {"#Enc":2,"#Clas":1}. This record does not assert independent reproduction.

### MixMo (Variant - Random Match)

NLL: 0.687. Result ID: 699ac8335698665ec4569e84.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294dd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a9a1e209131cea294dd.md>)

Recorded evaluation configuration: {"#Enc":1,"#Clas":2,"variant":"random association"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.