Machine Translation Meta-evaluation on WMT EN-ZH 2025
56.8Acc*EqMM (MLP)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MM (MLP)Pooling Strategy=Language-Pooled, Model Variant=MM, Combiner=MLP2026.05 | 56.8 | 81.8 | |
| MM (MLP)Pooling Strategy=Language-Separate, Model Variant=MM, Combiner=MLP2026.05 | 56.7 | 78.2 | |
| DMM (MLP)Pooling Strategy=Language-Pooled, Model Variant=DMM, Combiner=MLP, k=62026.05 | 56.7 | 81.5 | |
| DMM (MLP)Pooling Strategy=Language-Separate, Model Variant=DMM, Combiner=MLP, k=62026.05 | 56.7 | 80.7 | |
| MM (GP)Pooling Strategy=Language-Separate, Model Variant=MM, Combiner=GP2026.05 | 55.4 | 60.8 | |
| DMM (GP)Pooling Strategy=Language-Pooled, Model Variant=DMM, Combiner=GP, k=62026.05 | 55.3 | 63.3 | |
| MM (GP)Pooling Strategy=Language-Pooled, Model Variant=MM, Combiner=GP2026.05 | 54.8 | 66.6 | |
| wmt22-comet-da2026.05 | 54.4 | 62.6 | |
| DMM (CL)Pooling Strategy=Language-Pooled, Model Variant=DMM, Combiner=CL, k=62026.05 | 54.2 | 59.9 | |
| DMM (CL)Pooling Strategy=Language-Separate, Model Variant=DMM, Combiner=CL, k=62026.05 | 53.7 | 57.4 | |
| DMM (GP)Pooling Strategy=Language-Separate, Model Variant=DMM, Combiner=GP, k=62026.05 | 53.1 | 67.3 | |
| Gemini-2.5-Pro2026.05 | 53 | 85.1 | |
| MM (OLS)Pooling Strategy=Language-Separate, Model Variant=MM, Combiner=OLS2026.05 | 51 | 46.7 | |
| MM (OLS)Pooling Strategy=Language-Pooled, Model Variant=MM, Combiner=OLS2026.05 | 47.3 | 27.6 | |
| DMM (OLS)Pooling Strategy=Language-Pooled, Model Variant=DMM, Combiner=OLS, k=62026.05 | 46.3 | 19 | |
| DMM (OLS)Pooling Strategy=Language-Separate, Model Variant=DMM, Combiner=OLS, k=62026.05 | 44.9 | 17.5 | |
| gemba2026.05 | 35.3 | 79.3 |