# Table Question Answering on AITQA (test)

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

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

Data updated: 2026-02-26T05:41:37.626Z

Evaluation of model performance on the test split of the AITQA dataset for Table Question Answering, measured using EM and LLM Eval Avg.

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 Question Answering |
| Dataset (including any stated split) | AITQA (test) |
| Metric | EM |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [EM](<https://www.sota2.com/research/sota/table-question-answering-on-aitqa-test.md?metric=EM>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | EM | Result date | Report paper |
| --- | --- | --- | --- |
| OHD | 73.83 | Not recorded | 6981819ca8b01e76cc8e26df |
| OHD | 69.34 | Not recorded | 6981819ca8b01e76cc8e26df |
| TableLLaMA-7B | 68.35 | Not recorded | 6981819ca8b01e76cc8e26df |
| ST-RAPTOR | 60.55 | Not recorded | 6981819ca8b01e76cc8e26df |
| E5 | 56.4 | Not recorded | 6981819ca8b01e76cc8e26df |
| Chain-of-Table | 49.32 | Not recorded | 6981819ca8b01e76cc8e26df |

### OHD

EM: 73.83. Result ID: 699653f15698665ec498fead.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ca8b01e76cc8e26df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6981819ca8b01e76cc8e26df.md>)

Recorded evaluation configuration: {"Backbone":"TableLLaMA-7B"}. This record does not assert independent reproduction.

### OHD

EM: 69.34. Result ID: 699653f15698665ec498feab.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ca8b01e76cc8e26df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6981819ca8b01e76cc8e26df.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2-72b"}. This record does not assert independent reproduction.

### TableLLaMA-7B

EM: 68.35. Result ID: 699653f15698665ec498feac.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ca8b01e76cc8e26df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d31e209131cea58c01.md>)

Recorded evaluation configuration: {"Backbone":"TableLLaMA-7B"}. This record does not assert independent reproduction.

### ST-RAPTOR

EM: 60.55. Result ID: 699653f15698665ec498feaa.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ca8b01e76cc8e26df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b061e209131cea86468.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2-72b"}. This record does not assert independent reproduction.

### E5

EM: 56.4. Result ID: 699653f15698665ec498fea9.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ca8b01e76cc8e26df.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2-72b"}. This record does not assert independent reproduction.

### Chain-of-Table

EM: 49.32. Result ID: 699653f15698665ec498fea8.

[Reporting paper](<https://www.sota2.com/research/paper/6981819ca8b01e76cc8e26df.md>)

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

Recorded evaluation configuration: {"Backbone":"Qwen2-72b"}. This record does not assert independent reproduction.

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