Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Financial Question Answering on TAT-QA (test)
Loading...
74.96
Execution Accuracy
FinAgent-RAG
53.3488
58.9594
64.57
70.1806
May 6, 2026
Execution Accuracy
F1 Score
Updated 26d ago
Evaluation Results
Method
Method
Links
Execution Accuracy
F1 Score
FinAgent-RAG
Backbone=DeepSeek-V3
2026.05
74.96
78.13
IterRAG
Backbone=DeepSeek-V3
2026.05
69.34
72.51
CRAG
Backbone=DeepSeek-V3
2026.05
67.58
70.74
Self-RAG
Backbone=DeepSeek-V3
2026.05
66.12
69.23
ReAct
Backbone=DeepSeek-V3
2026.05
64.35
67.48
Advanced RAG
Backbone=DeepSeek-V3
2026.05
62.67
65.89
Naive RAG
Backbone=DeepSeek-V3
2026.05
58.93
62.14
FinMA
2026.05
57.41
60.73
Zero-shot LLM
Backbone=DeepSeek-V3
2026.05
54.18
57.32
Feedback
Search any
task
Search any
task