Complaint Drafting on J1 (eval)
87.7FOR ScoreLawThinker
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LawThinkerMethod Category=Autonomous Tool Usage within Reasoning, Base Model=Qwen3-32B2026.02 | 87.7 | 75.6 | |
| LawLLM-7BMethod Category=Direct Reasoning (Legal-specific LLMs)2026.02 | 74.2 | 69.9 | |
| Qwen2.5-7BMethod Category=Direct Reasoning (Multilingual LLMs)2026.02 | 73.1 | 76.9 | |
| Qwen3-32BMethod Category=Direct Reasoning (Multilingual LLMs)2026.02 | 71.4 | 66.4 | |
| Qwen3-14BMethod Category=Direct Reasoning (Multilingual LLMs)2026.02 | 69.3 | 77.5 | |
| Gemma3-12BMethod Category=Direct Reasoning (Multilingual LLMs)2026.02 | 57.2 | 77 | |
| Plan-and-SolveMethod Category=Workflow-based Methods, Base Model=Qwen3-32B2026.02 | 53.3 | 68.5 | |
| Search-o1Method Category=Autonomous Tool Usage within Reasoning, Base Model=Qwen3-32B2026.02 | 53.3 | 70.3 | |
| Plan-and-ExecuteMethod Category=Workflow-based Methods, Base Model=Qwen3-32B2026.02 | 53.1 | 62.8 | |
| GLM4-9BMethod Category=Direct Reasoning (Multilingual LLMs)2026.02 | 52.5 | 67 | |
| Ministral-8BMethod Category=Direct Reasoning (Multilingual LLMs)2026.02 | 50.5 | 65.3 | |
| ReActMethod Category=Workflow-based Methods, Base Model=Qwen3-32B2026.02 | 50.1 | 67.5 | |
| ChatLaw2-7BMethod Category=Direct Reasoning (Legal-specific LLMs)2026.02 | 30.3 | 24 | |
| Qwen3-8BMethod Category=Direct Reasoning (Multilingual LLMs)2026.02 | 7.5 | 57.9 |