# Masked Language Modeling on BLLIP (test)

Source: [Masked Language Modeling on BLLIP (test)](<https://www.sota2.com/research/sota/masked-language-modeling-on-bllip-test>)

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

Data updated: 2026-02-26T05:57:54.049Z

Evaluation of Masked Language Modeling performance on the test split of the BLLIP dataset, typically measured using Perplexity.

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 | Masked Language Modeling |
| Dataset (including any stated split) | BLLIP (test) |
| Metric | Perplexity |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| 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

- [Perplexity](<https://www.sota2.com/research/sota/masked-language-modeling-on-bllip-test.md?metric=Perplexity>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Perplexity | Result date | Report paper |
| --- | --- | --- | --- |
| Transformer | 101.91 | Not recorded | 68fa714b1e209131cea507cf |
| Probabilistic Transformer | 123.18 | Not recorded | 68fa714b1e209131cea507cf |

### Transformer

Perplexity: 101.91. Result ID: 6991c4e03a6c3148490a769a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa714b1e209131cea507cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

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

### Probabilistic Transformer

Perplexity: 123.18. Result ID: 6991c4e03a6c3148490a769b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa714b1e209131cea507cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa714b1e209131cea507cf.md>)

[Implementation](<https://github.com/whyNLP/Probabilistic-Transformer>)

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.
