Machine Translation on FLORES200 EN-TR
62.76chrF++Seed-X-PPO-7B
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Seed-X-PPO-7BSystem Category=Large Models or Extensive Data, Model Group=Translation-specific LLMs2026.02 | 62.76 | 78.94 | 91.4 | |
| Gemini-2.0-flashSystem Category=Large Models or Extensive Data, Model Group=General-purpose LLMs2026.02 | 59.46 | 79.48 | 92.1 | |
| OpenAI GPT-5.2System Category=Large Models or Extensive Data, Model Group=General-purpose LLMs2026.02 | 58.68 | 79.96 | 92.39 | |
| DeepSeek-V3.2System Category=Large Models or Extensive Data, Model Group=General-purpose LLMs2026.02 | 58.38 | 79.55 | 91.7 | |
| PEGRL-8BSystem Category=Resource-Constrained, Model Group=Ours2026.02 | 50.41 | 78.26 | 87.25 | |
| Qwen3-14BSystem Category=Resource-Constrained, Model Group=General-purpose LLMs2026.02 | 50.25 | 73.98 | 82.39 | |
| Qwen3-32BSystem Category=Resource-Constrained, Model Group=General-purpose LLMs2026.02 | 49.46 | 73.28 | 81.32 | |
| MT-R1-Zero-8BSystem Category=Resource-Constrained, Model Group=MT-R1-Zero2026.02 | 48.72 | 75.92 | 83.53 | |
| PEGRL-4BSystem Category=Resource-Constrained, Model Group=Ours2026.02 | 47.77 | 76.35 | 83.63 | |
| Qwen3-8BSystem Category=Resource-Constrained, Model Group=General-purpose LLMs2026.02 | 47.58 | 70.62 | 76.89 | |
| MT-R1-Zero-4BSystem Category=Resource-Constrained, Model Group=MT-R1-Zero2026.02 | 45.22 | 72.7 | 78.14 | |
| Qwen3-4BSystem Category=Resource-Constrained, Model Group=General-purpose LLMs2026.02 | 42.34 | 61.61 | 65.91 |