# Machine Translation Performance Prediction on FLORES-AE33 Type I (test) Source: [Machine Translation Performance Prediction on FLORES-AE33 Type I (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:49:00.672Z Evaluation of models predicting the quality of Machine Translation outputs on the FLORES-AE33 Type I test set, typically measured using regression metrics like MAE, RMSE, and Pearson's r. 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 | Machine Translation Performance Prediction | | Dataset (including any stated split) | FLORES-AE33 Type I (test) | | Metric | MAE | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 12 of 12 | | 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](): Lower is better; unit: SCALAR. - [RMSE](): Lower is better; unit: SCALAR. - [Pearson's r](): Higher is better; unit: SCALAR. ## Recorded results | Method | MAE | Result date | Report paper | | --- | --- | --- | --- | | RT-SCORE | 1.8 | Not recorded | 68fa6f531e209131cea450ee | | RT-SCORE | 2.13 | Not recorded | 68fa6f531e209131cea450ee | | RT-SCORE | 2.87 | Not recorded | 68fa6f531e209131cea450ee | | RT-SCORE | 3.51 | Not recorded | 68fa6f531e209131cea450ee | | RT-SCORE | 3.86 | Not recorded | 68fa6f531e209131cea450ee | | RT-SCORE | 3.97 | Not recorded | 68fa6f531e209131cea450ee | | RT-SCORE | 4.09 | Not recorded | 68fa6f531e209131cea450ee | | RT-SCORE | 4.22 | Not recorded | 68fa6f531e209131cea450ee | | RT-SCORE | 4.35 | Not recorded | 68fa6f531e209131cea450ee | | RT-SCORE | 4.98 | Not recorded | 68fa6f531e209131cea450ee | | RT-SCORE | 5.7 | Not recorded | 68fa6f531e209131cea450ee | | RT-SCORE | 6.06 | Not recorded | 68fa6f531e209131cea450ee | ### RT-SCORE MAE: 1.8. Result ID: 6990b87e3a6c31484902b995. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"MBART50-M2M","Translation Metric":"BLEU"}. This record does not assert independent reproduction. ### RT-SCORE MAE: 2.13. Result ID: 6990b87e3a6c31484902b996. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"MBART50-M2M","Translation Metric":"spBLEU"}. This record does not assert independent reproduction. ### RT-SCORE MAE: 2.87. Result ID: 6990b87e3a6c31484902b9a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"GOOGLE-TRANS","Translation Metric":"BERTScore"}. This record does not assert independent reproduction. ### RT-SCORE MAE: 3.51. Result ID: 6990b87e3a6c31484902b997. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"MBART50-M2M","Translation Metric":"chrF"}. This record does not assert independent reproduction. ### RT-SCORE MAE: 3.86. Result ID: 6990b87e3a6c31484902b999. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"M2M-100-BASE","Translation Metric":"BLEU"}. This record does not assert independent reproduction. ### RT-SCORE MAE: 3.97. Result ID: 6990b87e3a6c31484902b99a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"M2M-100-BASE","Translation Metric":"spBLEU"}. This record does not assert independent reproduction. ### RT-SCORE MAE: 4.09. Result ID: 6990b87e3a6c31484902b99d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"GOOGLE-TRANS","Translation Metric":"BLEU"}. This record does not assert independent reproduction. ### RT-SCORE MAE: 4.22. Result ID: 6990b87e3a6c31484902b99e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"GOOGLE-TRANS","Translation Metric":"spBLEU"}. This record does not assert independent reproduction. ### RT-SCORE MAE: 4.35. Result ID: 6990b87e3a6c31484902b99c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"M2M-100-BASE","Translation Metric":"BERTScore"}. This record does not assert independent reproduction. ### RT-SCORE MAE: 4.98. Result ID: 6990b87e3a6c31484902b998. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"MBART50-M2M","Translation Metric":"BERTScore"}. This record does not assert independent reproduction. ### RT-SCORE MAE: 5.7. Result ID: 6990b87e3a6c31484902b99f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"GOOGLE-TRANS","Translation Metric":"chrF"}. This record does not assert independent reproduction. ### RT-SCORE MAE: 6.06. Result ID: 6990b87e3a6c31484902b99b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"MT System":"M2M-100-BASE","Translation Metric":"chrF"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.