Question Answering on FinanceBench (test)
42.74F1 ScoreSelf-RAG
Evaluation Results
| Method | Links | |
|---|---|---|
| Self-RAG2026.01 | 42.74 | |
| Token-Guard2026.01 | 30.8 | |
| Self-Reflection2026.01 | 19.37 | |
| SELF-REFINE2026.01 | 17.09 | |
| BaseModel2026.01 | 16 |
| Method | Links | |
|---|---|---|
| Self-RAG2026.01 | 42.74 | |
| Token-Guard2026.01 | 30.8 | |
| Self-Reflection2026.01 | 19.37 | |
| SELF-REFINE2026.01 | 17.09 | |
| BaseModel2026.01 | 16 |