List your company

Financial Auditing on FinMR

82.09Joint AccuracyAUDITFLOW
-1.73420.02841.7963.552Jun 2, 2026

Evaluation results

MethodLinks
AUDITFLOWBackbone=GPT-5.52026.0682.09
AUDITFLOWBackbone=GPT-4o2026.0680.6
AUDITFLOWBackbone=Sonnet 4.62026.0680.6
AUDITFLOWBackbone=Qwen-397B2026.0680.6
AUDITFLOWBackbone=Qwen-27B2026.0673.13
Single AgentBackbone=GPT-5.52026.0667.16
Single AgentBackbone=GPT-4o2026.0667.16
Single AgentBackbone=Sonnet 4.62026.0667.16
Single AgentBackbone=Qwen-397B2026.0667.16
HerculeanBackbone=GPT-5.52026.0665.67
HerculeanBackbone=GPT-4o2026.0665.67
HerculeanBackbone=Sonnet 4.62026.0665.67
Single AgentBackbone=Qwen-27B2026.0664.18
GraphRAGBackbone=GPT-5.52026.0648.39
GraphRAGBackbone=Sonnet 4.62026.0646.77
TreeRAGBackbone=GPT-5.52026.0643.28
HerculeanBackbone=Qwen-397B2026.0643.28
TreeRAGBackbone=Sonnet 4.62026.0641.79
GraphRAGBackbone=GPT-4o2026.0638.1
HerculeanBackbone=Qwen-27B2026.0637.31
TreeRAGBackbone=GPT-4o2026.0635.82
TreeRAGBackbone=Qwen-397B2026.0632.84
AUDITFLOWBackbone=Fino1-14B2026.0631.34
Single AgentBackbone=Fino1-14B2026.0629.85
HerculeanBackbone=Fino1-14B2026.0628.35
GraphRAGBackbone=Qwen-397B2026.0627.42
TreeRAGBackbone=Qwen-27B2026.0623.88
GraphRAGBackbone=Qwen-27B2026.0622.39
TreeRAGBackbone=Fino1-14B2026.0620.9
GraphRAGBackbone=Fino1-14B2026.0617.91
FinAuditingBackbone=GPT-5.52026.0614.93
FinAuditingBackbone=Fino1-14B2026.0614.93
Direct LLMBackbone=Qwen-397B2026.068.96
FinAuditingBackbone=Sonnet 4.62026.067.46
Direct LLMBackbone=GPT-5.52026.067.46
Direct LLMBackbone=Fino1-14B2026.067.46
Vanilla RAGBackbone=GPT-5.52026.067.46
Vanilla RAGBackbone=Qwen-27B2026.067.46
FinAuditingBackbone=GPT-4o2026.065.97
FinAuditingBackbone=Qwen-397B2026.065.97
Direct LLMBackbone=GPT-4o2026.065.97
FinAuditingBackbone=Qwen-27B2026.064.48
Vanilla RAGBackbone=Qwen-397B2026.064.48
Vanilla RAGBackbone=Sonnet 4.62026.062.99
Direct LLMBackbone=Sonnet 4.62026.061.49
Direct LLMBackbone=Qwen-27B2026.061.49
Vanilla RAGBackbone=GPT-4o2026.061.49
Vanilla RAGBackbone=Fino1-14B2026.061.49