# Text-to-SQL on Spider Robustness Suite SYN REALISTIC DK (dev)

Source: [Text-to-SQL on Spider Robustness Suite SYN REALISTIC DK (dev)](<https://www.sota2.com/research/sota/text-to-sql-on-spider-robustness-suite-syn-realistic-dk-dev>)

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

Data updated: 2026-02-26T05:42:33.991Z

Evaluation of Text-to-SQL performance on the Spider Robustness Suite, specifically measuring Execution Accuracy across the SYN, REALISTIC, and DK components using the development split data.

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) | Spider Robustness Suite SYN REALISTIC DK (dev) |
| Metric | Execution Accuracy (SYN) |
| 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

- [Execution Accuracy (SYN)](<https://www.sota2.com/research/sota/text-to-sql-on-spider-robustness-suite-syn-realistic-dk-dev.md?metric=Execution%20Accuracy%20(SYN)>): Higher is better; unit: PERCENT.

- [Execution Accuracy (REALISTIC)](<https://www.sota2.com/research/sota/text-to-sql-on-spider-robustness-suite-syn-realistic-dk-dev.md?metric=Execution%20Accuracy%20(REALISTIC)>): Higher is better; unit: PERCENT.

- [Execution Accuracy (DK)](<https://www.sota2.com/research/sota/text-to-sql-on-spider-robustness-suite-syn-realistic-dk-dev.md?metric=Execution%20Accuracy%20(DK)>): Higher is better; unit: PERCENT.

- [Average Execution Accuracy](<https://www.sota2.com/research/sota/text-to-sql-on-spider-robustness-suite-syn-realistic-dk-dev.md?metric=Average%20Execution%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Execution Accuracy (SYN) | Result date | Report paper |
| --- | --- | --- | --- |
| SQLForge-LM | 78.9 | Not recorded | 68fa7b801e209131cea88b5d |
| SENSE | 77.6 | Not recorded | 68fa7b801e209131cea88b5d |
| CodeS | 77 | Not recorded | 68fa7b801e209131cea88b5d |
| RESDSQL | 76.9 | Not recorded | 68fa7b801e209131cea88b5d |
| SQLForge-LM | 74.6 | Not recorded | 68fa7b801e209131cea88b5d |
| SENSE | 72.6 | Not recorded | 68fa7b801e209131cea88b5d |

### SQLForge-LM

Execution Accuracy (SYN): 78.9. Result ID: 698b86027a967eddb76f4da4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b801e209131cea88b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b801e209131cea88b5d.md>)

Recorded evaluation configuration: {"Backbone":"CodeLlama-13B","Multiple Calls":false}. This record does not assert independent reproduction.

### SENSE

Execution Accuracy (SYN): 77.6. Result ID: 698b86027a967eddb76f4da1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b801e209131cea88b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa745f1e209131cea6141c.md>)

Recorded evaluation configuration: {"Backbone":"CodeLlama-13B","Multiple Calls":false}. This record does not assert independent reproduction.

### CodeS

Execution Accuracy (SYN): 77. Result ID: 698b86027a967eddb76f4da2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b801e209131cea88b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa725b1e209131cea55eca.md>)

Recorded evaluation configuration: {"Backbone":"StarCoder-15B","Multiple Calls":false}. This record does not assert independent reproduction.

### RESDSQL

Execution Accuracy (SYN): 76.9. Result ID: 698b86027a967eddb76f4d9f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b801e209131cea88b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f0a1e209131cea43835.md>)

[Implementation](<https://github.com/RUCKBReasoning/RESDSQL>)

Recorded evaluation configuration: {"Backbone":"ROBERTa-3B","Multiple Calls":true}. This record does not assert independent reproduction.

### SQLForge-LM

Execution Accuracy (SYN): 74.6. Result ID: 698b86027a967eddb76f4da3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b801e209131cea88b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b801e209131cea88b5d.md>)

Recorded evaluation configuration: {"Backbone":"CodeLlama-7B","Multiple Calls":false}. This record does not assert independent reproduction.

### SENSE

Execution Accuracy (SYN): 72.6. Result ID: 698b86027a967eddb76f4da0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b801e209131cea88b5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa745f1e209131cea6141c.md>)

Recorded evaluation configuration: {"Backbone":"CodeLlama-7B","Multiple Calls":false}. This record does not assert independent reproduction.

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