Machine Translation on WMT EN–TR 24
57.42chrF++Gemini-2.0-flash
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Gemini-2.0-flashSystem Category=Large Models or Extensive Data, Model Group=General-purpose LLMs2026.02 | 57.42 | 68.05 | 77.65 | |
| DeepSeek-V3.2System Category=Large Models or Extensive Data, Model Group=General-purpose LLMs2026.02 | 56.21 | 68.13 | 77.84 | |
| OpenAI GPT-5.2System Category=Large Models or Extensive Data, Model Group=General-purpose LLMs2026.02 | 56.14 | 69.45 | 77.87 | |
| Seed-X-PPO-7BSystem Category=Large Models or Extensive Data, Model Group=Translation-specific LLMs2026.02 | 54.28 | 67.28 | 75.99 | |
| PEGRL-8BSystem Category=Resource-Constrained, Model Group=Ours2026.02 | 48.04 | 68.14 | 73.51 | |
| Qwen3-14BSystem Category=Resource-Constrained, Model Group=General-purpose LLMs2026.02 | 47.56 | 63.26 | 67.82 | |
| Qwen3-32BSystem Category=Resource-Constrained, Model Group=General-purpose LLMs2026.02 | 47.18 | 62.66 | 66.47 | |
| MT-R1-Zero-8BSystem Category=Resource-Constrained, Model Group=MT-R1-Zero2026.02 | 47.1 | 63.96 | 68.98 | |
| PEGRL-4BSystem Category=Resource-Constrained, Model Group=Ours2026.02 | 45.39 | 65.49 | 69.24 | |
| Qwen3-8BSystem Category=Resource-Constrained, Model Group=General-purpose LLMs2026.02 | 44.82 | 59.25 | 63.04 | |
| MT-R1-Zero-4BSystem Category=Resource-Constrained, Model Group=MT-R1-Zero2026.02 | 43.25 | 61.57 | 63.85 | |
| Qwen3-4BSystem Category=Resource-Constrained, Model Group=General-purpose LLMs2026.02 | 40.12 | 50.6 | 53.89 |