List your company

Safety and Utility Evaluation on Finance

0.004JSRMENTOR
-0.028880.193060.4150.63694Nov 10, 2025

Evaluation results

MethodLinks
MENTORTarget Model=Qwen3-235B2025.110.0044.918
DPP-MENTORTarget Model=GPT-4o2025.110.0064.368
MENTORTarget Model=DeepSeek-R12025.110.0064.856
MENTORTarget Model=Average2025.110.0094.72
DPP-MENTORTarget Model=Qwen3-235B2025.110.014.908
DPP-MENTORTarget Model=Average2025.110.0134.684
RePDTarget Model=Qwen3-235B2025.110.0162.007
Self-ReminderTarget Model=Qwen3-235B2025.110.0164.544
MENTORTarget Model=GPT-4o2025.110.0164.386
DPP-MENTORTarget Model=DeepSeek-R12025.110.0244.776
G4D-RuleTreeTarget Model=Qwen3-235B2025.110.0284.516
G4DTarget Model=Qwen3-235B2025.110.034.642
G4D-RuleTreeTarget Model=Average2025.110.0514.563
G4D-RuleTreeTarget Model=DeepSeek-R12025.110.0584.7
G4D-RuleTreeTarget Model=GPT-4o2025.110.0684.472
Self-ReminderTarget Model=Average2025.110.0724.539
G4DTarget Model=Average2025.110.0724.632
Self-ReminderTarget Model=GPT-4o2025.110.084.396
G4DTarget Model=GPT-4o2025.110.0924.534
G4DTarget Model=DeepSeek-R12025.110.0944.72
Self-ReminderTarget Model=DeepSeek-R12025.110.124.678
RePDTarget Model=DeepSeek-R12025.110.1894.441
RePDTarget Model=Average2025.110.1922.745
DPPTarget Model=Qwen3-235B2025.110.2684.77
ProBTarget Model=Qwen3-235B2025.110.2884.316
VanillaTarget Model=Qwen3-235B2025.110.34.854
RPO-MENTORTarget Model=Qwen3-235B2025.110.3224.796
RePDTarget Model=GPT-4o2025.110.3721.788
RPOTarget Model=Qwen3-235B2025.110.3924.892
ProBTarget Model=Average2025.110.4694.279
ProBTarget Model=DeepSeek-R12025.110.4784.456
RPO-MENTORTarget Model=Average2025.110.4794.581
RPO-MENTORTarget Model=DeepSeek-R12025.110.4844.78
VanillaTarget Model=DeepSeek-R12025.110.5224.924
DPPTarget Model=Average2025.110.5354.752
VanillaTarget Model=Average2025.110.5494.809
RPOTarget Model=Average2025.110.5634.737
RPOTarget Model=DeepSeek-R12025.110.5724.878
DPPTarget Model=DeepSeek-R12025.110.5864.922
RPO-MENTORTarget Model=GPT-4o2025.110.6324.166
ProBTarget Model=GPT-4o2025.110.6424.066
RPOTarget Model=GPT-4o2025.110.7264.442
DPPTarget Model=GPT-4o2025.110.754.564
VanillaTarget Model=GPT-4o2025.110.8264.65