Machine Translation Ranking on NT20 Zh→En
62.6AccuracyGemini-2.5-Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-2.5-ProParadigm=GQM, Reasoning Strategy=with Reasoning2026.02 | 62.6 | |
| DeepSeek-R1-0528Paradigm=GQM, Reasoning Strategy=with Reasoning2026.02 | 61.98 | |
| BT-RMParadigm=SQM, Reasoning Strategy=without Reasoning2026.02 | 58.16 | |
| CometKiwi-XXLParadigm=SQM, Reasoning Strategy=without Reasoning2026.02 | 57.82 | |
| GRRM (RLVR)Paradigm=GQM, Reasoning Strategy=with Reasoning, Training Phase=RLVR2026.02 | 57.77 | |
| GRRM (SFT)Paradigm=GQM, Reasoning Strategy=with Reasoning, Training Phase=SFT2026.02 | 56.77 | |
| Gemini-2.5-ProParadigm=SQM, Reasoning Strategy=with Reasoning2026.02 | 53.56 | |
| SQM-GenRM (RLVR)Paradigm=SQM, Reasoning Strategy=with Reasoning, Training Phase=RLVR2026.02 | 49.21 | |
| DeepSeek-R1-0528Paradigm=SQM, Reasoning Strategy=with Reasoning2026.02 | 48.42 | |
| SQM-GenRM (SFT)Paradigm=SQM, Reasoning Strategy=with Reasoning, Training Phase=SFT2026.02 | 47.18 | |
| RandomParadigm=N/A2026.02 | 39.42 |