Machine Translation on lexical choice (val+test)
54.15BLEUgpt-4o
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| gpt-4oReasoning=XML-style2025.10 | 54.15 | 69.41 | 0.9208 | 0.8797 | 0.31 | |
| gpt-4Reasoning=XML-style2025.10 | 53.99 | 68.79 | 0.9179 | 0.8713 | 2.58 | |
| gpt-4oReasoning=None2025.10 | 53.84 | 69.67 | 0.9223 | 0.8851 | — | |
| gpt-4Reasoning=None2025.10 | 51.41 | 66.63 | 0.9128 | 0.8643 | — | |
| gpt-4-turboReasoning=None2025.10 | 49.56 | 65.67 | 0.912 | 0.8683 | — | |
| gpt-3.5-turboReasoning=XML-style2025.10 | 49.42 | 65.69 | 0.9102 | 0.856 | 2.11 | |
| gpt-4-turboReasoning=XML-style2025.10 | 49.25 | 64.84 | 0.8911 | 0.8557 | -0.31 | |
| gpt-3.5-turboReasoning=None2025.10 | 47.31 | 64.88 | 0.9061 | 0.8619 | — | |
| Llama3.3Reasoning=XML-style2025.10 | 46.58 | 63.37 | 0.9005 | 0.8449 | 0.15 | |
| Llama3.3Reasoning=None2025.10 | 46.43 | 62.47 | 0.9023 | 0.8479 | — | |
| Phi-4Reasoning=XML-style2025.10 | 44.35 | 61.37 | 0.9 | 0.8355 | 1.77 | |
| Phi-4Reasoning=None2025.10 | 42.58 | 59.63 | 0.8936 | 0.8334 | — | |
| DeepSeek-R1 32BReasoning=XML-style2025.10 | 40.94 | 58.26 | 0.8816 | 0.814 | 2.07 | |
| DeepSeek-R1 32BReasoning=None2025.10 | 38.87 | 56.25 | 0.8827 | 0.8194 | — | |
| DeepSeek-R1 14BReasoning=None2025.10 | 38.43 | 55.13 | 0.8732 | 0.8031 | — | |
| Llama3.1Reasoning=None2025.10 | 35.08 | 52.1 | 0.8717 | 0.7925 | — | |
| DeepSeek-R1 14BReasoning=XML-style2025.10 | 33.33 | 51.14 | 0.8506 | 0.7701 | -5.1 | |
| DeepSeek-R1 8BReasoning=None2025.10 | 30.89 | 48.33 | 0.8558 | 0.7632 | — | |
| DeepSeek-R1 8BReasoning=XML-style2025.10 | 30.26 | 48.05 | 0.8331 | 0.7517 | -0.63 | |
| Llama3.1Reasoning=XML-style2025.10 | 29.37 | 48.57 | 0.8573 | 0.7664 | -5.71 | |
| MistralReasoning=XML-style2025.10 | 27.79 | 45 | 0.849 | 0.7537 | 1.17 | |
| MistralReasoning=None2025.10 | 26.62 | 44.89 | 0.8444 | 0.7436 | — | |
| Llama3.2Reasoning=None2025.10 | 25.19 | 42.47 | 0.8311 | 0.7297 | — | |
| Llama3.2Reasoning=XML-style2025.10 | 22.38 | 43.1 | 0.819 | 0.7041 | -2.81 |