Machine Translation Meta-evaluation on MENT EN-ZH
80.4Meta ScoreRATE
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| RATEEvaluation Level=System-Level, Metric Category=LLM-as-a-Judge2026.01 | 80.4 | 88.9 | 97.7 | 92.7 | |
| RATEEvaluation Level=Segment-Level, Metric Category=LLM-as-a-Judge2026.01 | 80.4 | 59.5 | 65.3 | 60.1 | |
| GEMBA-DAEvaluation Level=System-Level, Metric Category=LLM-as-a-Judge2026.01 | 77.2 | 91.1 | 94.5 | 95.2 | |
| GEMBA-DAEvaluation Level=Segment-Level, Metric Category=LLM-as-a-Judge2026.01 | 77.2 | 56.7 | 68.4 | 60.5 | |
| COMETEvaluation Level=System-Level, Metric Category=Reference-based Metrics2026.01 | 69 | 82.2 | 92 | 79.4 | |
| COMETEvaluation Level=Segment-Level, Metric Category=Reference-based Metrics2026.01 | 69 | 56.5 | 50.3 | 38.8 | |
| GEMBA-MQMEvaluation Level=System-Level, Metric Category=LLM-as-a-Judge2026.01 | 68.7 | 91.1 | 97.2 | 93.9 | |
| GEMBA-MQMEvaluation Level=Segment-Level, Metric Category=LLM-as-a-Judge2026.01 | 68.7 | 52.1 | 58.2 | 42.6 | |
| M-MADEvaluation Level=System-Level, Metric Category=LLM-as-a-Judge2026.01 | 65.8 | 88.9 | 95.2 | 90.3 | |
| M-MADEvaluation Level=Segment-Level, Metric Category=LLM-as-a-Judge2026.01 | 65.8 | 51.5 | 50.1 | 45.2 | |
| ThinMQMEvaluation Level=System-Level, Metric Category=LLM-as-a-Judge2026.01 | 65.1 | 91.1 | 91.5 | 91.5 | |
| ThinMQMEvaluation Level=Segment-Level, Metric Category=LLM-as-a-Judge2026.01 | 65.1 | 50.4 | 43.8 | 43.2 | |
| BLEUEvaluation Level=System-Level, Metric Category=Reference-based Metrics2026.01 | 64.9 | 91.1 | 92.6 | 91.5 | |
| BLEUEvaluation Level=Segment-Level, Metric Category=Reference-based Metrics2026.01 | 64.9 | 56.6 | 37 | 39.5 | |
| BLEURTEvaluation Level=System-Level, Metric Category=Reference-based Metrics2026.01 | 56.5 | 57.8 | 82.5 | 17.6 | |
| BLEURTEvaluation Level=Segment-Level, Metric Category=Reference-based Metrics2026.01 | 56.5 | 50.5 | 28.5 | 21.8 | |
| MetricX-24Evaluation Level=System-Level, Metric Category=Reference-based Metrics2026.01 | 56.2 | 66.7 | 83.5 | 29.7 | |
| MetricX-24Evaluation Level=Segment-Level, Metric Category=Reference-based Metrics2026.01 | 56.2 | 54.5 | 47.1 | 33 | |
| XCOMETEvaluation Level=System-Level, Metric Category=Reference-based Metrics2026.01 | 54.5 | 68.9 | 86.6 | 40.6 | |
| XCOMETEvaluation Level=Segment-Level, Metric Category=Reference-based Metrics2026.01 | 54.5 | 52 | 31.1 | 25.8 | |
| MetricX-23Evaluation Level=System-Level, Metric Category=Reference-based Metrics2026.01 | 52.2 | 64.4 | 83.6 | 27.3 | |
| MetricX-23Evaluation Level=Segment-Level, Metric Category=Reference-based Metrics2026.01 | 52.2 | 53.2 | 41.2 | 29.4 | |
| EAPromptEvaluation Level=System-Level, Metric Category=LLM-as-a-Judge2026.01 | 47.4 | 75.6 | 92.4 | 67.3 | |
| EAPromptEvaluation Level=Segment-Level, Metric Category=LLM-as-a-Judge2026.01 | 47.4 | 43.3 | 12.2 | 9.1 | |
| COMETKiwiEvaluation Level=System-Level, Metric Category=Reference-free (QE) Metrics2026.01 | 42.8 | 48.9 | 79.5 | -1.8 | |
| COMETKiwiEvaluation Level=Segment-Level, Metric Category=Reference-free (QE) Metrics2026.01 | 42.8 | 52.3 | 37.8 | 26.9 | |
| MetricX24-QEEvaluation Level=System-Level, Metric Category=Reference-free (QE) Metrics2026.01 | 41.7 | 55.6 | 79.3 | 12.7 | |
| MetricX24-QEEvaluation Level=Segment-Level, Metric Category=Reference-free (QE) Metrics2026.01 | 41.7 | 51.8 | 41.5 | 25.4 | |
| MetricX23-QEEvaluation Level=System-Level, Metric Category=Reference-free (QE) Metrics2026.01 | 31.9 | 35.6 | 79.4 | -28.5 | |
| MetricX23-QEEvaluation Level=Segment-Level, Metric Category=Reference-free (QE) Metrics2026.01 | 31.9 | 50.2 | 39.9 | 20.8 |