# Class-conditional sampling on MNIST (test)

Source: [Class-conditional sampling on MNIST (test)](<https://www.sota2.com/research/sota/class-conditional-sampling-on-mnist-test>)

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

Data updated: 2026-02-26T05:34:05.387Z

Evaluation of class-conditional sampling performance on the test split of the MNIST dataset, reporting metrics related to sample quality and accuracy (ACCL, ACCE).

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 | Class-conditional sampling |
| Dataset (including any stated split) | MNIST (test) |
| Metric | Accuracy (ACCL) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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 (ACCL)](<https://www.sota2.com/research/sota/class-conditional-sampling-on-mnist-test.md?metric=Accuracy%20(ACCL)>): Higher is better; unit: PERCENT.

- [Accuracy (ACCE)](<https://www.sota2.com/research/sota/class-conditional-sampling-on-mnist-test.md?metric=Accuracy%20(ACCE)>): Higher is better; unit: PERCENT.

- [Effective Sample Size](<https://www.sota2.com/research/sota/class-conditional-sampling-on-mnist-test.md?metric=Effective%20Sample%20Size>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy (ACCL) | Result date | Report paper |
| --- | --- | --- | --- |
| TFTF | 99.66 | Not recorded | 6992a4769ebc499c97406bf0 |
| FLOWCHEF | 91.15 | Not recorded | 6992a4769ebc499c97406bf0 |
| FMPS | 62.86 | Not recorded | 6992a4769ebc499c97406bf0 |

### TFTF

Accuracy (ACCL): 99.66. Result ID: 699a5fad5698665ec4e79f93.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf0.md>)

Recorded evaluation configuration: {"Algorithm":"Algorithm 1","K":16}. This record does not assert independent reproduction.

### FLOWCHEF

Accuracy (ACCL): 91.15. Result ID: 699a5fad5698665ec4e79f92.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FMPS

Accuracy (ACCL): 62.86. Result ID: 699a5fad5698665ec4e79f91.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4769ebc499c97406bf0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a8b1e209131cea83ceb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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