# Legal Translation on HKCFA Judgment 97-22 Source: [Legal Translation on HKCFA Judgment 97-22]() Collection index: [llms.txt]() Data updated: 2026-06-19T06:22:57.534Z Evaluation of Legal Translation performance using the HKCFA Judgment 97-22 dataset, reporting metrics such as xCOMET-XL and wmt22-unite-da. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Legal Translation | | Dataset (including any stated split) | HKCFA Judgment 97-22 | | Metric | xCOMET-XL | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 26 of 26 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [xCOMET-XL](): Higher is better; unit: SCALAR. - [wmt22-unite-da](): Higher is better; unit: SCALAR. - [Average Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | xCOMET-XL | Result date | Report paper | | --- | --- | --- | --- | | GPT-4o | 85.12 | Not recorded | 68fa79d01e209131cea7f832 | | GPT-4 | 84.24 | Not recorded | 68fa79d01e209131cea7f832 | | MoE-16B | 83.53 | Not recorded | 68fa79d01e209131cea7f832 | | R1-Distill-32B | 83.25 | Not recorded | 68fa79d01e209131cea7f832 | | ChatGPT | 82.29 | Not recorded | 68fa79d01e209131cea7f832 | | 14B-Chat | 81.86 | Not recorded | 68fa79d01e209131cea7f832 | | 13B-Chat | 81.33 | Not recorded | 68fa79d01e209131cea7f832 | | 7B-Chat | 80.54 | Not recorded | 68fa79d01e209131cea7f832 | | 3-6B | 80.27 | Not recorded | 68fa79d01e209131cea7f832 | | 13B-Base | 79.6 | Not recorded | 68fa79d01e209131cea7f832 | | 33B | 79.29 | Not recorded | 68fa79d01e209131cea7f832 | | 2-6B | 78.11 | Not recorded | 68fa79d01e209131cea7f832 | | 13B | 76.26 | Not recorded | 68fa79d01e209131cea7f832 | | GPT-4o | 69.42 | Not recorded | 68fa79d01e209131cea7f832 | | GPT-4 | 68.1 | Not recorded | 68fa79d01e209131cea7f832 | | MoE-16B | 67.45 | Not recorded | 68fa79d01e209131cea7f832 | | R1-Distill-32B | 67.12 | Not recorded | 68fa79d01e209131cea7f832 | | ChatGPT | 66.15 | Not recorded | 68fa79d01e209131cea7f832 | | 14B-Chat | 65.55 | Not recorded | 68fa79d01e209131cea7f832 | | 13B-Chat | 64.4 | Not recorded | 68fa79d01e209131cea7f832 | | 7B-Chat | 63.9 | Not recorded | 68fa79d01e209131cea7f832 | | 3-6B | 63.85 | Not recorded | 68fa79d01e209131cea7f832 | | 33B | 62.5 | Not recorded | 68fa79d01e209131cea7f832 | | 13B-Base | 62.2 | Not recorded | 68fa79d01e209131cea7f832 | | 2-6B | 61.1 | Not recorded | 68fa79d01e209131cea7f832 | | 13B | 58.5 | Not recorded | 68fa79d01e209131cea7f832 | ### GPT-4o xCOMET-XL: 85.12. Result ID: 6a34dfebfbc373592c3192b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"OpenAI"}. This record does not assert independent reproduction. ### GPT-4 xCOMET-XL: 84.24. Result ID: 6a34dfebfbc373592c3192ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"OpenAI"}. This record does not assert independent reproduction. ### MoE-16B xCOMET-XL: 83.53. Result ID: 6a34dfebfbc373592c3192be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"DeepSeek"}. This record does not assert independent reproduction. ### R1-Distill-32B xCOMET-XL: 83.25. Result ID: 6a34dfebfbc373592c3192c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"DeepSeek"}. This record does not assert independent reproduction. ### ChatGPT xCOMET-XL: 82.29. Result ID: 6a34dfebfbc373592c3192bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"OpenAI"}. This record does not assert independent reproduction. ### 14B-Chat xCOMET-XL: 81.86. Result ID: 6a34dfebfbc373592c3192c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"Qwen"}. This record does not assert independent reproduction. ### 13B-Chat xCOMET-XL: 81.33. Result ID: 6a34dfebfbc373592c3192c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"Baichuan"}. This record does not assert independent reproduction. ### 7B-Chat xCOMET-XL: 80.54. Result ID: 6a34dfebfbc373592c3192c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"Qwen"}. This record does not assert independent reproduction. ### 3-6B xCOMET-XL: 80.27. Result ID: 6a34dfebfbc373592c3192ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"ChatGLM"}. This record does not assert independent reproduction. ### 13B-Base xCOMET-XL: 79.6. Result ID: 6a34dfebfbc373592c3192c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"Baichuan"}. This record does not assert independent reproduction. ### 33B xCOMET-XL: 79.29. Result ID: 6a34dfebfbc373592c3192ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"ChatLaw"}. This record does not assert independent reproduction. ### 2-6B xCOMET-XL: 78.11. Result ID: 6a34dfebfbc373592c3192cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"ChatGLM"}. This record does not assert independent reproduction. ### 13B xCOMET-XL: 76.26. Result ID: 6a34dfebfbc373592c3192d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"TransLaw","Series":"ChatLaw"}. This record does not assert independent reproduction. ### GPT-4o xCOMET-XL: 69.42. Result ID: 6a34dfebfbc373592c3192b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"OpenAI"}. This record does not assert independent reproduction. ### GPT-4 xCOMET-XL: 68.1. Result ID: 6a34dfebfbc373592c3192bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"OpenAI"}. This record does not assert independent reproduction. ### MoE-16B xCOMET-XL: 67.45. Result ID: 6a34dfebfbc373592c3192bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"DeepSeek"}. This record does not assert independent reproduction. ### R1-Distill-32B xCOMET-XL: 67.12. Result ID: 6a34dfebfbc373592c3192c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"DeepSeek"}. This record does not assert independent reproduction. ### ChatGPT xCOMET-XL: 66.15. Result ID: 6a34dfebfbc373592c3192bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"OpenAI"}. This record does not assert independent reproduction. ### 14B-Chat xCOMET-XL: 65.55. Result ID: 6a34dfebfbc373592c3192c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"Qwen"}. This record does not assert independent reproduction. ### 13B-Chat xCOMET-XL: 64.4. Result ID: 6a34dfebfbc373592c3192c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"Baichuan"}. This record does not assert independent reproduction. ### 7B-Chat xCOMET-XL: 63.9. Result ID: 6a34dfebfbc373592c3192c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"Qwen"}. This record does not assert independent reproduction. ### 3-6B xCOMET-XL: 63.85. Result ID: 6a34dfebfbc373592c3192cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"ChatGLM"}. This record does not assert independent reproduction. ### 33B xCOMET-XL: 62.5. Result ID: 6a34dfebfbc373592c3192cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"ChatLaw"}. This record does not assert independent reproduction. ### 13B-Base xCOMET-XL: 62.2. Result ID: 6a34dfebfbc373592c3192c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"Baichuan"}. This record does not assert independent reproduction. ### 2-6B xCOMET-XL: 61.1. Result ID: 6a34dfebfbc373592c3192cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"ChatGLM"}. This record does not assert independent reproduction. ### 13B xCOMET-XL: 58.5. Result ID: 6a34dfebfbc373592c3192d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"Single Translator Agent","Series":"ChatLaw"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.