# Free-form Table Question Answering on FeTaQA (test)

Source: [Free-form Table Question Answering on FeTaQA (test)](<https://www.sota2.com/research/sota/free-form-table-question-answering-on-fetaqa-test>)

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

Data updated: 2026-02-26T05:36:56.267Z

Evaluation of model performance on the test split of the FeTaQA dataset for Free-form Table Question Answering.

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 | Free-form Table Question Answering |
| Dataset (including any stated split) | FeTaQA (test) |
| Metric | BLEU |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [BLEU](<https://www.sota2.com/research/sota/free-form-table-question-answering-on-fetaqa-test.md?metric=BLEU>): Higher is better; unit: SCALAR.

- [ROUGE-1](<https://www.sota2.com/research/sota/free-form-table-question-answering-on-fetaqa-test.md?metric=ROUGE-1>): Higher is better; unit: SCALAR.

- [ROUGE-2](<https://www.sota2.com/research/sota/free-form-table-question-answering-on-fetaqa-test.md?metric=ROUGE-2>): Higher is better; unit: SCALAR.

- [ROUGE-L](<https://www.sota2.com/research/sota/free-form-table-question-answering-on-fetaqa-test.md?metric=ROUGE-L>): Higher is better; unit: SCALAR.

## Recorded results

| Method | BLEU | Result date | Report paper |
| --- | --- | --- | --- |
| CHAIN-OF-TABLE | 0.3261 | Not recorded | 68fa71d71e209131cea534db |
| Codex w/ DATER | 0.3092 | Not recorded | 68fa6f251e209131cea4409c |
| T5-large | 0.3054 | Not recorded | 68fa6f251e209131cea4409c |
| Dater | 0.2947 | Not recorded | 68fa71d71e209131cea534db |
| End-to-End QA | 0.2837 | Not recorded | 68fa71d71e209131cea534db |
| T5-base | 0.2814 | Not recorded | 68fa6f251e209131cea4409c |
| Codex | 0.2796 | Not recorded | 68fa6f251e209131cea4409c |
| T5-small | 0.216 | Not recorded | 68fa6f251e209131cea4409c |

### CHAIN-OF-TABLE

BLEU: 0.3261. Result ID: 6991e9153a6c3148490b6485.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71d71e209131cea534db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d71e209131cea534db.md>)

Recorded evaluation configuration: {"Model":"PaLM 2"}. This record does not assert independent reproduction.

### Codex w/ DATER

BLEU: 0.3092. Result ID: 699098263a6c31484901ba9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Implementation](<https://github.com/AlibabaResearch/DAMO-ConvAI>)

Recorded evaluation configuration: {"Evaluation Protocol":"LLM based"}. This record does not assert independent reproduction.

### T5-large

BLEU: 0.3054. Result ID: 699098263a6c31484901ba98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuning based"}. This record does not assert independent reproduction.

### Dater

BLEU: 0.2947. Result ID: 6991e9153a6c3148490b6484.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71d71e209131cea534db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Implementation](<https://github.com/AlibabaResearch/DAMO-ConvAI>)

Recorded evaluation configuration: {"Model":"PaLM 2"}. This record does not assert independent reproduction.

### End-to-End QA

BLEU: 0.2837. Result ID: 6991e9153a6c3148490b6483.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71d71e209131cea534db.md>)

Recorded evaluation configuration: {"Model":"PaLM 2"}. This record does not assert independent reproduction.

### T5-base

BLEU: 0.2814. Result ID: 699098263a6c31484901ba97.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuning based"}. This record does not assert independent reproduction.

### Codex

BLEU: 0.2796. Result ID: 699098263a6c31484901ba99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5f1e209131cea27ced.md>)

[Implementation](<https://www.github.com/openai/human-eval>)

Recorded evaluation configuration: {"Evaluation Protocol":"LLM based"}. This record does not assert independent reproduction.

### T5-small

BLEU: 0.216. Result ID: 699098263a6c31484901ba96.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f251e209131cea4409c.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuning based"}. This record does not assert independent reproduction.

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