List your company

Civil Court on J1 EVAL

50.3PFS ScoreLawThinker
1.52414.18726.8539.513Feb 12, 2026

Evaluation results

MethodLinks
LawThinkerMethod Category=Autonomous Tool Usage within Reasoning, Base Model=Qwen3-32B2026.0250.328.54423.2
Gemma3-12BMethod Category=Direct Reasoning (Multilingual LLMs)2026.0242.717.732.814.8
Qwen3-32BMethod Category=Direct Reasoning (Multilingual LLMs)2026.0242.516.735.717.3
Search-o1Method Category=Autonomous Tool Usage within Reasoning, Base Model=Qwen3-32B2026.0240.620.536.321.2
Plan-and-ExecuteMethod Category=Workflow-based Methods, Base Model=Qwen3-32B2026.0240.523.842.620.5
ReActMethod Category=Workflow-based Methods, Base Model=Qwen3-32B2026.0239.221.638.320.8
Plan-and-SolveMethod Category=Workflow-based Methods, Base Model=Qwen3-32B2026.023823.438.719.4
Qwen2.5-7BMethod Category=Direct Reasoning (Multilingual LLMs)2026.0223.49.1208.5
GLM4-9BMethod Category=Direct Reasoning (Multilingual LLMs)2026.0220.85.916.54.7
Ministral-8BMethod Category=Direct Reasoning (Multilingual LLMs)2026.0215.15.710.14.3
Qwen3-8BMethod Category=Direct Reasoning (Multilingual LLMs)2026.0212.99.923.114.7
Qwen3-14BMethod Category=Direct Reasoning (Multilingual LLMs)2026.026.84.15.93.9
ChatLaw2-7BMethod Category=Direct Reasoning (Legal-specific LLMs)2026.023.75.67.8—
LawLLM-7BMethod Category=Direct Reasoning (Legal-specific LLMs)2026.023.4———