# Translation Score Prediction on FLORES-AE33 Type III

Source: [Translation Score Prediction on FLORES-AE33 Type III](<https://www.sota2.com/research/sota/translation-score-prediction-on-flores-ae33-type-iii>)

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

Data updated: 2026-02-26T05:49:01.087Z

Evaluation of models predicting the quality scores (MAE, RMSE, Pearson's r) for machine translation outputs specifically on the FLORES-AE33 Type III dataset variant.

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 | Translation Score Prediction |
| Dataset (including any stated split) | FLORES-AE33 Type III |
| Metric | MAE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [MAE](<https://www.sota2.com/research/sota/translation-score-prediction-on-flores-ae33-type-iii.md?metric=MAE>): Lower is better; unit: SCALAR.

- [RMSE](<https://www.sota2.com/research/sota/translation-score-prediction-on-flores-ae33-type-iii.md?metric=RMSE>): Lower is better; unit: SCALAR.

- [Pearson's r](<https://www.sota2.com/research/sota/translation-score-prediction-on-flores-ae33-type-iii.md?metric=Pearson%27s%20r>): Higher is better; unit: SCALAR.

## Recorded results

| Method | MAE | Result date | Report paper |
| --- | --- | --- | --- |
| RT-SCORE Regressor | 0.81 | Not recorded | 68fa6f531e209131cea450ee |
| RT-SCORE Regressor | 1.2 | Not recorded | 68fa6f531e209131cea450ee |
| RT-SCORE Regressor | 2.99 | Not recorded | 68fa6f531e209131cea450ee |
| RT-SCORE Regressor | 3.04 | Not recorded | 68fa6f531e209131cea450ee |
| RT-SCORE Regressor | 3.18 | Not recorded | 68fa6f531e209131cea450ee |
| RT-SCORE Regressor | 4.29 | Not recorded | 68fa6f531e209131cea450ee |
| RT-SCORE Regressor | 5.08 | Not recorded | 68fa6f531e209131cea450ee |
| RT-SCORE Regressor | 5.42 | Not recorded | 68fa6f531e209131cea450ee |

### RT-SCORE Regressor

MAE: 0.81. Result ID: 6990b87e3a6c31484902b9d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

Recorded evaluation configuration: {"MT System":"MBART50-M2M","MT System Status":"seen","Trans. Metric":"BLEU"}. This record does not assert independent reproduction.

### RT-SCORE Regressor

MAE: 1.2. Result ID: 6990b87e3a6c31484902b9d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

Recorded evaluation configuration: {"MT System":"MBART50-M2M","MT System Status":"seen","Trans. Metric":"spBLEU"}. This record does not assert independent reproduction.

### RT-SCORE Regressor

MAE: 2.99. Result ID: 6990b87e3a6c31484902b9d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

Recorded evaluation configuration: {"MT System":"M2M-100-BASE","MT System Status":"unseen","Trans. Metric":"BLEU"}. This record does not assert independent reproduction.

### RT-SCORE Regressor

MAE: 3.04. Result ID: 6990b87e3a6c31484902b9d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

Recorded evaluation configuration: {"MT System":"MBART50-M2M","MT System Status":"seen","Trans. Metric":"chrF"}. This record does not assert independent reproduction.

### RT-SCORE Regressor

MAE: 3.18. Result ID: 6990b87e3a6c31484902b9da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

Recorded evaluation configuration: {"MT System":"M2M-100-BASE","MT System Status":"unseen","Trans. Metric":"spBLEU"}. This record does not assert independent reproduction.

### RT-SCORE Regressor

MAE: 4.29. Result ID: 6990b87e3a6c31484902b9dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

Recorded evaluation configuration: {"MT System":"M2M-100-BASE","MT System Status":"unseen","Trans. Metric":"BERTScore"}. This record does not assert independent reproduction.

### RT-SCORE Regressor

MAE: 5.08. Result ID: 6990b87e3a6c31484902b9d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

Recorded evaluation configuration: {"MT System":"MBART50-M2M","MT System Status":"seen","Trans. Metric":"BERTScore"}. This record does not assert independent reproduction.

### RT-SCORE Regressor

MAE: 5.42. Result ID: 6990b87e3a6c31484902b9db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f531e209131cea450ee.md>)

Recorded evaluation configuration: {"MT System":"M2M-100-BASE","MT System Status":"unseen","Trans. Metric":"chrF"}. This record does not assert independent reproduction.

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