# Text-to-SQL on Termite (test)

Source: [Text-to-SQL on Termite (test)](<https://www.sota2.com/research/sota/text-to-sql-on-termite-test>)

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

Data updated: 2026-02-26T05:34:15.010Z

Evaluation of Text-to-SQL performance on the test split of the Termite dataset, measured by accuracy across different difficulty levels (Easy, Medium, Hard, Extra-Hard).

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 | Text-to-SQL |
| Dataset (including any stated split) | Termite (test) |
| Metric | Accuracy (Easy) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Accuracy (Easy)](<https://www.sota2.com/research/sota/text-to-sql-on-termite-test.md?metric=Accuracy%20(Easy)>): Higher is better; unit: PERCENT.

- [Accuracy (Medium)](<https://www.sota2.com/research/sota/text-to-sql-on-termite-test.md?metric=Accuracy%20(Medium)>): Higher is better; unit: PERCENT.

- [Accuracy (Hard)](<https://www.sota2.com/research/sota/text-to-sql-on-termite-test.md?metric=Accuracy%20(Hard)>): Higher is better; unit: PERCENT.

- [Accuracy (Extra-Hard)](<https://www.sota2.com/research/sota/text-to-sql-on-termite-test.md?metric=Accuracy%20(Extra-Hard)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Easy) | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-3.5 | 74 | Not recorded | 68fa76151e209131cea6b52e |
| GPT-3.5 | 62 | Not recorded | 68fa76151e209131cea6b52e |

### GPT-3.5

Accuracy (Easy): 74. Result ID: 699424c03a6c3148491b5c56.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76151e209131cea6b52e.md>)

Recorded evaluation configuration: {"Data Condition":"Original Dumps","Evaluation Scenario":"zero-shot"}. This record does not assert independent reproduction.

### GPT-3.5

Accuracy (Easy): 62. Result ID: 699424c03a6c3148491b5c57.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76151e209131cea6b52e.md>)

Recorded evaluation configuration: {"Data Condition":"Adversarial Table Disconnection","Evaluation Scenario":"zero-shot"}. This record does not assert independent reproduction.

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