# Language Generation on Synthetic data v1 (test)

Source: [Language Generation on Synthetic data v1 (test)](<https://www.sota2.com/research/sota/language-generation-on-synthetic-data-v1-test>)

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

Data updated: 2026-02-26T05:53:13.522Z

Evaluation of language generation models on the test split of the Synthetic data v1 dataset, assessed 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 | Language Generation |
| Dataset (including any stated split) | Synthetic data v1 (test) |
| Metric | NLL |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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/language-generation-on-synthetic-data-v1-test.md?metric=NLL>): Lower is better; unit: SCALAR.

## Recorded results

| Method | NLL | Result date | Report paper |
| --- | --- | --- | --- |
| RankGAN | 8.247 | Not recorded | 68fa64481e209131cea03b4c |
| SeqGAN | 8.736 | Not recorded | 68fa64481e209131cea03b4c |
| PG-BLEU | 8.946 | Not recorded | 68fa64481e209131cea03b4c |
| MLE | 9.038 | Not recorded | 68fa64481e209131cea03b4c |

### RankGAN

NLL: 8.247. Result ID: 698c2a65112aeb9460efe5e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03b4c.md>)

[Implementation](<https://github.com/LantaoYu/SeqGAN>)

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

### SeqGAN

NLL: 8.736. Result ID: 698c2a65112aeb9460efe5e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03b4c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63a01e209131ce9ffd47.md>)

[Implementation](<https://github.com/LantaoYu/SeqGAN>)

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

### PG-BLEU

NLL: 8.946. Result ID: 698c2a65112aeb9460efe5e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03b4c.md>)

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

### MLE

NLL: 9.038. Result ID: 698c2a65112aeb9460efe5e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03b4c.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.