# Table Question Answering on FinQA

Source: [Table Question Answering on FinQA](<https://www.sota2.com/research/sota/table-question-answering-on-finqa>)

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

Data updated: 2026-03-25T12:36:43.622Z

Evaluation of model performance on the FinQA dataset for Table Question Answering, measured by the Quality score metric.

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 | Table-QA |
| Dataset (including any stated split) | FinQA |
| Metric | Quality Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

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

## Recorded results

| Method | Quality Score | Result date | Report paper |
| --- | --- | --- | --- |
| Table-Specialist | 26.1 | Not recorded | 68fa753f1e209131cea66c30 |
| GPT-3.5 | 22.2 | Not recorded | 68fa753f1e209131cea66c30 |
| Table-Specialist | 14.5 | Not recorded | 68fa753f1e209131cea66c30 |
| Llama3.1-8B | 6.6 | Not recorded | 68fa753f1e209131cea66c30 |

### Table-Specialist

Quality Score: 26.1. Result ID: 69c3d6c147f34ce924ad100e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

Recorded evaluation configuration: {"Base Model":"GPT-3.5","Fine-tuning Protocol":"Specialist Fine-tuning"}. This record does not assert independent reproduction.

### GPT-3.5

Quality Score: 22.2. Result ID: 69c3d6c147f34ce924ad100d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Model Variant":"Vanilla"}. This record does not assert independent reproduction.

### Table-Specialist

Quality Score: 14.5. Result ID: 69c3d6c147f34ce924ad1010.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

Recorded evaluation configuration: {"Base Model":"Llama3.1-8B","Fine-tuning Protocol":"Specialist Fine-tuning"}. This record does not assert independent reproduction.

### Llama3.1-8B

Quality Score: 6.6. Result ID: 69c3d6c147f34ce924ad100f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753f1e209131cea66c30.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eae1e209131cea41685.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"Model Variant":"Vanilla"}. This record does not assert independent reproduction.

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