Machine Translation Ranking on NT20 En→Zh
66.49AccuracyCometKiwi-XXL
Evaluation Results
| Method | Links | |
|---|---|---|
| CometKiwi-XXLParadigm=SQM, Reasoning Strategy=without Reasoning2026.02 | 66.49 | |
| BT-RMParadigm=SQM, Reasoning Strategy=without Reasoning2026.02 | 66.49 | |
| Gemini-2.5-ProParadigm=GQM, Reasoning Strategy=with Reasoning2026.02 | 64.58 | |
| DeepSeek-R1-0528Paradigm=GQM, Reasoning Strategy=with Reasoning2026.02 | 64.38 | |
| GRRM (RLVR)Paradigm=GQM, Reasoning Strategy=with Reasoning, Training Phase=RLVR2026.02 | 62.17 | |
| GRRM (SFT)Paradigm=GQM, Reasoning Strategy=with Reasoning, Training Phase=SFT2026.02 | 59.45 | |
| Gemini-2.5-ProParadigm=SQM, Reasoning Strategy=with Reasoning2026.02 | 46.41 | |
| RandomParadigm=N/A2026.02 | 43.82 | |
| DeepSeek-R1-0528Paradigm=SQM, Reasoning Strategy=with Reasoning2026.02 | 43.67 | |
| SQM-GenRM (RLVR)Paradigm=SQM, Reasoning Strategy=with Reasoning, Training Phase=RLVR2026.02 | 39.42 | |
| SQM-GenRM (SFT)Paradigm=SQM, Reasoning Strategy=with Reasoning, Training Phase=SFT2026.02 | 37.21 |