List your company

Robustness Evaluation on Perturbation Dataset

62.56Change AccuracyL4L
-2.502414.388831.2848.1712Nov 26, 2025

Evaluation results

MethodLinks
L4L2025.1162.56
GPT-5.22025.1159.63
DeepSeek v32025.1155.93
Claude 4 Sonnet2025.1151.5
GPT-4o2025.1150.67
GPT o4-mini2025.1146.33
DISC-LawLLM2025.1123.17
LexiLaw2025.110