List your company

Financial Auditing on Financial Audit Evaluation Set 67 cases (test)

0SERFinAuditing
-3.880422.312348.50574.6977Jun 2, 2026

Evaluation results

MethodLinks
FinAuditingBackbone=GPT-5.52026.06016.4268.66
FinAuditingBackbone=GPT-4o2026.06019.474.63
FinAuditingBackbone=Sonnet 4.62026.06022.3970.15
HerculeanBackbone=GPT-5.52026.0605.9728.36
HerculeanBackbone=Sonnet 4.62026.060034.33
HerculeanBackbone=Qwen-397B2026.06011.9433.78
AUDITFLOWBackbone=Sonnet 4.62026.060019.4
FinAuditingBackbone=Qwen-397B2026.061.4920.8971.64
HerculeanBackbone=GPT-4o2026.061.498.9623.88
AUDITFLOWBackbone=GPT-5.52026.061.491.4914.93
AUDITFLOWBackbone=GPT-4o2026.061.49017.91
HerculeanBackbone=Qwen-27B2026.062.9911.9447.76
AUDITFLOWBackbone=Qwen-397B2026.062.99016.42
GraphRAGBackbone=GPT-5.52026.064.841.6145.16
AUDITFLOWBackbone=Qwen-27B2026.067.462.9916.42
GraphRAGBackbone=Sonnet 4.62026.0611.29041.94
Single AgentBackbone=GPT-5.52026.0613.431.4917.91
Single AgentBackbone=GPT-4o2026.0613.431.4917.91
Single AgentBackbone=Sonnet 4.62026.0613.431.4917.91
Single AgentBackbone=Qwen-397B2026.0613.431.4917.91
FinAuditingBackbone=Qwen-27B2026.0614.9329.8550.75
Single AgentBackbone=Qwen-27B2026.0616.421.4917.91
GraphRAGBackbone=GPT-4o2026.0617.466.3537.38
TreeRAGBackbone=GPT-4o2026.0620.891.4941.79
TreeRAGBackbone=GPT-5.52026.0632.842.9920.89
TreeRAGBackbone=Sonnet 4.62026.0634.331.4922.39
TreeRAGBackbone=Qwen-27B2026.0637.312.9935.82
Single AgentBackbone=Fino1-14B2026.0637.311.4931.34
AUDITFLOWBackbone=Fino1-14B2026.0637.311.4929.85
GraphRAGBackbone=Qwen-397B2026.0638.711.6132.26
TreeRAGBackbone=Qwen-397B2026.0638.817.4620.89
HerculeanBackbone=Fino1-14B2026.0643.2822.395.97
GraphRAGBackbone=Qwen-27B2026.0644.784.4828.36
TreeRAGBackbone=Fino1-14B2026.0644.787.4626.87
Direct LLMBackbone=Qwen-397B2026.0653.731.4935.82
Direct LLMBackbone=Fino1-14B2026.0656.728.9626.87
Direct LLMBackbone=GPT-5.52026.0659.72.9929.85
Direct LLMBackbone=GPT-4o2026.0659.72.9931.34
GraphRAGBackbone=Fino1-14B2026.0662.6914.934.48
Direct LLMBackbone=Qwen-27B2026.0664.181.4932.84
FinAuditingBackbone=Fino1-14B2026.0670.1511.942.99
Direct LLMBackbone=Sonnet 4.62026.0688.06010.45
Vanilla RAGBackbone=GPT-4o2026.0689.557.461.49
Vanilla RAGBackbone=GPT-5.52026.0692.5400
Vanilla RAGBackbone=Qwen-27B2026.0692.5400
Vanilla RAGBackbone=Fino1-14B2026.0694.031.492.99
Vanilla RAGBackbone=Qwen-397B2026.0695.5200
Vanilla RAGBackbone=Sonnet 4.62026.0697.0100