Machine Translation Ranking on GenMT22 MQM En→Ru
71.23AccuracyGemini-2.5-Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-2.5-ProParadigm=GQM, Reasoning Strategy=with Reasoning2026.02 | 71.23 | |
| DeepSeek-R1-0528Paradigm=GQM, Reasoning Strategy=with Reasoning2026.02 | 69.15 | |
| CometKiwi-XXLParadigm=SQM, Reasoning Strategy=without Reasoning2026.02 | 67.12 | |
| GRRM (RLVR)Paradigm=GQM, Reasoning Strategy=with Reasoning, Training Phase=RLVR2026.02 | 66.67 | |
| BT-RMParadigm=SQM, Reasoning Strategy=without Reasoning2026.02 | 66.1 | |
| Gemini-2.5-ProParadigm=SQM, Reasoning Strategy=with Reasoning2026.02 | 64.88 | |
| GRRM (SFT)Paradigm=GQM, Reasoning Strategy=with Reasoning, Training Phase=SFT2026.02 | 64.8 | |
| DeepSeek-R1-0528Paradigm=SQM, Reasoning Strategy=with Reasoning2026.02 | 59.13 | |
| SQM-GenRM (RLVR)Paradigm=SQM, Reasoning Strategy=with Reasoning, Training Phase=RLVR2026.02 | 54.82 | |
| SQM-GenRM (SFT)Paradigm=SQM, Reasoning Strategy=with Reasoning, Training Phase=SFT2026.02 | 51.84 | |
| RandomParadigm=N/A2026.02 | 37.64 |