# Legal Contract Revision on MAUD Source: [Legal Contract Revision on MAUD]() Collection index: [llms.txt]() Data updated: 2026-04-14T10:11:51.025Z Evaluation of model performance on revising legal contracts using the MAUD dataset. 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 Contract Revision | | Dataset (including any stated split) | MAUD | | Metric | CQ Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 25 of 25 | | 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 - [CQ Score](): Higher is better; unit: PERCENT. - [RRR Score](): Higher is better; unit: PERCENT. - [TES Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | CQ Score | Result date | Report paper | | --- | --- | --- | --- | | RCBSF | 86.89 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RCBSF | 83.45 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RCBSF | 80.77 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Iteration | 80.45 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RAG | 79.56 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RCBSF | 78.91 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Iteration | 77.45 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RAG | 76.56 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RAG | 75.34 | Not recorded | 69ddca1e7d0172140ec79aa1 | | CoT | 75.12 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RCBSF | 74.88 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Iteration | 74.23 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Iteration | 73.45 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Standard | 73.45 | Not recorded | 69ddca1e7d0172140ec79aa1 | | CoT | 72.12 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RAG | 71.56 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Iteration | 70.23 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Standard | 69.88 | Not recorded | 69ddca1e7d0172140ec79aa1 | | CoT | 69.88 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RAG | 68.89 | Not recorded | 69ddca1e7d0172140ec79aa1 | | CoT | 67.89 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Standard | 67.45 | Not recorded | 69ddca1e7d0172140ec79aa1 | | CoT | 66.45 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Standard | 65.34 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Standard | 65.15 | Not recorded | 69ddca1e7d0172140ec79aa1 | ### RCBSF CQ Score: 86.89. Result ID: 69de12de47f34ce924c60f2c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Chat"}. This record does not assert independent reproduction. ### RCBSF CQ Score: 83.45. Result ID: 69de12de47f34ce924c60f18. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction. ### RCBSF CQ Score: 80.77. Result ID: 69de12de47f34ce924c60f22. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LawLLM-7B"}. This record does not assert independent reproduction. ### Iteration CQ Score: 80.45. Result ID: 69de12de47f34ce924c60f2b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Chat"}. This record does not assert independent reproduction. ### RAG CQ Score: 79.56. Result ID: 69de12de47f34ce924c60f2a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Chat"}. This record does not assert independent reproduction. ### RCBSF CQ Score: 78.91. Result ID: 69de12de47f34ce924c60f1d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B"}. This record does not assert independent reproduction. ### Iteration CQ Score: 77.45. Result ID: 69de12de47f34ce924c60f17. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction. ### RAG CQ Score: 76.56. Result ID: 69de12de47f34ce924c60f16. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction. ### RAG CQ Score: 75.34. Result ID: 69de12de47f34ce924c60f20. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LawLLM-7B"}. This record does not assert independent reproduction. ### CoT CQ Score: 75.12. Result ID: 69de12de47f34ce924c60f29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Chat"}. This record does not assert independent reproduction. ### RCBSF CQ Score: 74.88. Result ID: 69de12de47f34ce924c60f27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LexiLaw-6B"}. This record does not assert independent reproduction. ### Iteration CQ Score: 74.23. Result ID: 69de12de47f34ce924c60f21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LawLLM-7B"}. This record does not assert independent reproduction. ### Iteration CQ Score: 73.45. Result ID: 69de12de47f34ce924c60f1c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B"}. This record does not assert independent reproduction. ### Standard CQ Score: 73.45. Result ID: 69de12de47f34ce924c60f28. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Chat"}. This record does not assert independent reproduction. ### CoT CQ Score: 72.12. Result ID: 69de12de47f34ce924c60f15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction. ### RAG CQ Score: 71.56. Result ID: 69de12de47f34ce924c60f1b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mistral-7B"}. This record does not assert independent reproduction. ### Iteration CQ Score: 70.23. Result ID: 69de12de47f34ce924c60f26. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LexiLaw-6B"}. This record does not assert independent reproduction. ### Standard CQ Score: 69.88. Result ID: 69de12de47f34ce924c60f14. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction. ### CoT CQ Score: 69.88. Result ID: 69de12de47f34ce924c60f1f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LawLLM-7B"}. This record does not assert independent reproduction. ### RAG CQ Score: 68.89. Result ID: 69de12de47f34ce924c60f25. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LexiLaw-6B"}. This record does not assert independent reproduction. ### CoT CQ Score: 67.89. Result ID: 69de12de47f34ce924c60f1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B"}. This record does not assert independent reproduction. ### Standard CQ Score: 67.45. Result ID: 69de12de47f34ce924c60f1e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"LawLLM-7B"}. This record does not assert independent reproduction. ### CoT CQ Score: 66.45. Result ID: 69de12de47f34ce924c60f24. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LexiLaw-6B"}. This record does not assert independent reproduction. ### Standard CQ Score: 65.34. Result ID: 69de12de47f34ce924c60f19. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B"}. This record does not assert independent reproduction. ### Standard CQ Score: 65.15. Result ID: 69de12de47f34ce924c60f23. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"LexiLaw-6B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.