# Machine Translation Meta-evaluation on WMT EN-JA 2025 Source: [Machine Translation Meta-evaluation on WMT EN-JA 2025]() Collection index: [llms.txt]() Data updated: 2026-05-12T11:16:34.875Z Evaluation of machine translation quality for the English-to-Japanese (EN-JA) language pair using meta-evaluation metrics on the WMT 2025 test set. 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 Meta-evaluation | | Dataset (including any stated split) | WMT EN-JA 2025 | | Metric | Acc\*Eq | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Acc\*Eq](): Higher is better; unit: PERCENT. - [SPA](): Higher is better; unit: PERCENT. ## Recorded results | Method | Acc\*Eq | Result date | Report paper | | --- | --- | --- | --- | | DMM (CL) | 57.3 | Not recorded | 6a02b45bdbc836b87d8249ca | | DMM (CL) | 57.1 | Not recorded | 6a02b45bdbc836b87d8249ca | | MM (GP) | 57 | Not recorded | 6a02b45bdbc836b87d8249ca | | DMM (MLP) | 56.8 | Not recorded | 6a02b45bdbc836b87d8249ca | | MM (MLP) | 56.7 | Not recorded | 6a02b45bdbc836b87d8249ca | | MM (MLP) | 56.6 | Not recorded | 6a02b45bdbc836b87d8249ca | | DMM (GP) | 56.6 | Not recorded | 6a02b45bdbc836b87d8249ca | | DMM (MLP) | 56.2 | Not recorded | 6a02b45bdbc836b87d8249ca | | Gemini-2.5-Pro | 55.9 | Not recorded | 6a02b45bdbc836b87d8249ca | | MM (GP) | 55.9 | Not recorded | 6a02b45bdbc836b87d8249ca | | DMM (GP) | 55.1 | Not recorded | 6a02b45bdbc836b87d8249ca | | wmt22-comet-da | 53.6 | Not recorded | 6a02b45bdbc836b87d8249ca | | MM (OLS) | 53.4 | Not recorded | 6a02b45bdbc836b87d8249ca | | MM (OLS) | 49.4 | Not recorded | 6a02b45bdbc836b87d8249ca | | DMM (OLS) | 49.4 | Not recorded | 6a02b45bdbc836b87d8249ca | | DMM (OLS) | 47.9 | Not recorded | 6a02b45bdbc836b87d8249ca | | gemba | 34.1 | Not recorded | 6a02b45bdbc836b87d8249ca | ### DMM (CL) Acc\*Eq: 57.3. Result ID: 6a030c0347f34ce924e6c95e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Pooled","Model Variant":"DMM","Combiner":"CL","k":"6"}. This record does not assert independent reproduction. ### DMM (CL) Acc\*Eq: 57.1. Result ID: 6a030c0347f34ce924e6c962. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Separate","Model Variant":"DMM","Combiner":"CL","k":"6"}. This record does not assert independent reproduction. ### MM (GP) Acc\*Eq: 57. Result ID: 6a030c0347f34ce924e6c955. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Pooled","Model Variant":"MM","Combiner":"GP"}. This record does not assert independent reproduction. ### DMM (MLP) Acc\*Eq: 56.8. Result ID: 6a030c0347f34ce924e6c961. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Separate","Model Variant":"DMM","Combiner":"MLP","k":"6"}. This record does not assert independent reproduction. ### MM (MLP) Acc\*Eq: 56.7. Result ID: 6a030c0347f34ce924e6c95a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Separate","Model Variant":"MM","Combiner":"MLP"}. This record does not assert independent reproduction. ### MM (MLP) Acc\*Eq: 56.6. Result ID: 6a030c0347f34ce924e6c957. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Pooled","Model Variant":"MM","Combiner":"MLP"}. This record does not assert independent reproduction. ### DMM (GP) Acc\*Eq: 56.6. Result ID: 6a030c0347f34ce924e6c95b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Pooled","Model Variant":"DMM","Combiner":"GP","k":"6"}. This record does not assert independent reproduction. ### DMM (MLP) Acc\*Eq: 56.2. Result ID: 6a030c0347f34ce924e6c95d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Pooled","Model Variant":"DMM","Combiner":"MLP","k":"6"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Acc\*Eq: 55.9. Result ID: 6a030c0347f34ce924e6c952. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MM (GP) Acc\*Eq: 55.9. Result ID: 6a030c0347f34ce924e6c958. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Separate","Model Variant":"MM","Combiner":"GP"}. This record does not assert independent reproduction. ### DMM (GP) Acc\*Eq: 55.1. Result ID: 6a030c0347f34ce924e6c95f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Separate","Model Variant":"DMM","Combiner":"GP","k":"6"}. This record does not assert independent reproduction. ### wmt22-comet-da Acc\*Eq: 53.6. Result ID: 6a030c0347f34ce924e6c953. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MM (OLS) Acc\*Eq: 53.4. Result ID: 6a030c0347f34ce924e6c959. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Separate","Model Variant":"MM","Combiner":"OLS"}. This record does not assert independent reproduction. ### MM (OLS) Acc\*Eq: 49.4. Result ID: 6a030c0347f34ce924e6c956. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Pooled","Model Variant":"MM","Combiner":"OLS"}. This record does not assert independent reproduction. ### DMM (OLS) Acc\*Eq: 49.4. Result ID: 6a030c0347f34ce924e6c960. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Separate","Model Variant":"DMM","Combiner":"OLS","k":"6"}. This record does not assert independent reproduction. ### DMM (OLS) Acc\*Eq: 47.9. Result ID: 6a030c0347f34ce924e6c95c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pooling Strategy":"Language-Pooled","Model Variant":"DMM","Combiner":"OLS","k":"6"}. This record does not assert independent reproduction. ### gemba Acc\*Eq: 34.1. Result ID: 6a030c0347f34ce924e6c954. [Reporting paper]() [Method origin paper]() 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.