# Financial Question Answering on TAT-QA (test)

Source: [Financial Question Answering on TAT-QA (test)](<https://www.sota2.com/research/sota/financial-question-answering-on-tat-qa-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-08T07:37:06.994Z

Evaluation of model performance on the test split of the TAT-QA dataset for Financial Question Answering, reporting Execution Accuracy and F1 scores.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Financial Question Answering |
| Dataset (including any stated split) | TAT-QA (test) |
| Metric | Execution Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Execution Accuracy](<https://www.sota2.com/research/sota/financial-question-answering-on-tat-qa-test.md?metric=Execution%20Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/financial-question-answering-on-tat-qa-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Execution Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FinAgent-RAG | 74.96 | Not recorded | 69fd6de95497b3b670c892a9 |
| IterRAG | 69.34 | Not recorded | 69fd6de95497b3b670c892a9 |
| CRAG | 67.58 | Not recorded | 69fd6de95497b3b670c892a9 |
| Self-RAG | 66.12 | Not recorded | 69fd6de95497b3b670c892a9 |
| ReAct | 64.35 | Not recorded | 69fd6de95497b3b670c892a9 |
| Advanced RAG | 62.67 | Not recorded | 69fd6de95497b3b670c892a9 |
| Naive RAG | 58.93 | Not recorded | 69fd6de95497b3b670c892a9 |
| FinMA | 57.41 | Not recorded | 69fd6de95497b3b670c892a9 |
| Zero-shot LLM | 54.18 | Not recorded | 69fd6de95497b3b670c892a9 |

### FinAgent-RAG

Execution Accuracy: 74.96. Result ID: 69fd929d47f34ce924e03fdf.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6de95497b3b670c892a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6de95497b3b670c892a9.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3"}. This record does not assert independent reproduction.

### IterRAG

Execution Accuracy: 69.34. Result ID: 69fd929d47f34ce924e03fde.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6de95497b3b670c892a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e48a.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3"}. This record does not assert independent reproduction.

### CRAG

Execution Accuracy: 67.58. Result ID: 69fd929d47f34ce924e03fdd.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6de95497b3b670c892a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75111e209131cea65797.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3"}. This record does not assert independent reproduction.

### Self-RAG

Execution Accuracy: 66.12. Result ID: 69fd929d47f34ce924e03fdc.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6de95497b3b670c892a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e51e209131cea4dc1c.md>)

[Implementation](<https://selfrag.github.io/>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3"}. This record does not assert independent reproduction.

### ReAct

Execution Accuracy: 64.35. Result ID: 69fd929d47f34ce924e03fdb.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6de95497b3b670c892a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb41e209131cea41992.md>)

[Implementation](<https://react-lm.github.io/>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3"}. This record does not assert independent reproduction.

### Advanced RAG

Execution Accuracy: 62.67. Result ID: 69fd929d47f34ce924e03fda.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6de95497b3b670c892a9.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3"}. This record does not assert independent reproduction.

### Naive RAG

Execution Accuracy: 58.93. Result ID: 69fd929d47f34ce924e03fd9.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6de95497b3b670c892a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b91e209131cea23c26.md>)

[Implementation](<https://github.com/huggingface/transformers/blob/master/examples/rag/>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3"}. This record does not assert independent reproduction.

### FinMA

Execution Accuracy: 57.41. Result ID: 69fd929d47f34ce924e03fd8.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6de95497b3b670c892a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fbc1e209131cea471fe.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Zero-shot LLM

Execution Accuracy: 54.18. Result ID: 69fd929d47f34ce924e03fd7.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6de95497b3b670c892a9.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.