# Text-to-SQL on Spider (test)

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

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

Data updated: 2026-07-07T09:22:40.545Z

Evaluation of Text-to-SQL performance on the test split of the Spider dataset, measured by metrics such as Execution Accuracy (EX (%)) and Retrieval Latency.

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 (test) |
| Metric | Execution Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 403 of 403 |
| 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](<https://www.sota2.com/research/sota/text-to-sql-on-spider-test.md?metric=Execution%20Accuracy>): Higher is better; unit: PERCENT.

- [Retrieval Latency](<https://www.sota2.com/research/sota/text-to-sql-on-spider-test.md?metric=Retrieval%20Latency>): Lower is better; unit: TIME.

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

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

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

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

- [Rouge-L](<https://www.sota2.com/research/sota/text-to-sql-on-spider-test.md?metric=Rouge-L>): Higher is better; unit: PERCENT.

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

- [EX (†)](<https://www.sota2.com/research/sota/text-to-sql-on-spider-test.md?metric=EX%20(%E2%80%A0)>): Higher is better; unit: PERCENT.

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

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

- [Qwen3 Score](<https://www.sota2.com/research/sota/text-to-sql-on-spider-test.md?metric=Qwen3%20Score>): Higher is better; unit: PERCENT.

- [DeepSeek-V2 Score](<https://www.sota2.com/research/sota/text-to-sql-on-spider-test.md?metric=DeepSeek-V2%20Score>): Higher is better; unit: PERCENT.

- [GPT-5 Score](<https://www.sota2.com/research/sota/text-to-sql-on-spider-test.md?metric=GPT-5%20Score>): Higher is better; unit: PERCENT.

- [Gemini-2.5 Score](<https://www.sota2.com/research/sota/text-to-sql-on-spider-test.md?metric=Gemini-2.5%20Score>): Higher is better; unit: PERCENT.

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

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

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

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

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

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

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

- [VES](<https://www.sota2.com/research/sota/text-to-sql-on-spider-test.md?metric=VES>): Higher is better; unit: SCALAR.

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

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

## Recorded results

| Method | Execution Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MiniSeek | 91.2 | Not recorded | 68fa78ab1e209131cea79c5f |
| MARS-SQL | 89.75 | Not recorded | 6909886c3ef7ccd74e5e5946 |
| MARS-SQL | 89.75 | Not recorded | 6909886c3ef7ccd74e5e5946 |
| XiYan-SQL | 89.65 | Not recorded | 68fa76e01e209131cea6f8eb |
| XiYan-SQL | 89.65 | Not recorded | 6909886c3ef7ccd74e5e5946 |
| MCS-SQL + GPT-4 | 89.6 | Not recorded | 68fa75031e209131cea65402 |
| MCS-SQL | 89.6 | Not recorded | 68fa76e01e209131cea6f8eb |
| MCS-SQL + GPT-4 | 89.6 | Not recorded | 69608b6853fdd5c36174423d |
| MCS-SQL | 89.6 | Not recorded | 6a22586f86173ad9c1468975 |
| MCS-SQL | 89.6 | Not recorded | 6a3b64a6206542251d7c9726 |
| Gemini3-Pro | 89.5 | Not recorded | 68fa78481e209131cea7799a |
| EXPO-SQL | 89.5 | Not recorded | 6a3b64a6206542251d7c9726 |
| Arctic-SQL-R1 | 89.4 | Not recorded | 6a3b64a6206542251d7c9726 |
| EXPO-SQL | 89.1 | Not recorded | 6a3b64a6206542251d7c9726 |
| OmniSQL-7B | 88.9 | Not recorded | 6a3b64a6206542251d7c9726 |
| Arctic-Text2SQL-R1 | 88.8 | Not recorded | 6909886c3ef7ccd74e5e5946 |
| Arctic-SQL-R1 | 88.8 | Not recorded | 6a3b64a6206542251d7c9726 |
| SQL-R1 | 88.7 | Not recorded | 6a22586f86173ad9c1468975 |
| SQL-R1 | 88.7 | Not recorded | 6a3b64a6206542251d7c9726 |
| KE-ICL | 88.68 | Not recorded | 6a13d77f6f71c5ae7dc9e7eb |
| CodeS | 88.31 | Not recorded | 6a13d77f6f71c5ae7dc9e7eb |
| SQL-R1 | 88.1 | Not recorded | 6a3b64a6206542251d7c9726 |
| KE-RL | 87.97 | Not recorded | 6a13d77f6f71c5ae7dc9e7eb |
| OmniSQL-7B | 87.9 | Not recorded | 69608b6853fdd5c36174423d |
| BASE-SQL | 87.9 | Not recorded | 6a22586f86173ad9c1468975 |
| OmniSQL | 87.9 | Not recorded | 6a22586f86173ad9c1468975 |
| CHASE-SQL | 87.6 | Not recorded | 68fa7b801e209131cea88b5d |
| PET-SQL | 87.6 | Not recorded | 68fa73661e209131cea5c396 |
| CHASE-SQL + Gemini 1.5 | 87.6 | Not recorded | 68fa75031e209131cea65402 |
| CHASE-SQL | 87.6 | Not recorded | 68fa76e01e209131cea6f8eb |
| PET-SQL | 87.6 | Not recorded | 68fa76e01e209131cea6f8eb |
| CHASE-SQL + Gemini | 87.6 | Not recorded | 6909886c3ef7ccd74e5e5946 |
| OmniSQL | 87.6 | Not recorded | 6909886c3ef7ccd74e5e5946 |
| CHASE-SQL | 87.6 | Not recorded | 6a3b64a6206542251d7c9726 |
| SQLForge-LM | 87.4 | Not recorded | 68fa7b801e209131cea88b5d |
| CHESS | 87.2 | Not recorded | 68fa75031e209131cea65402 |
| CHESS | 87.2 | Not recorded | 68fa78ab1e209131cea79c5f |
| CHESS | 87.2 | Not recorded | 6909886c3ef7ccd74e5e5946 |
| DAIL-SQL | 87.2 | Not recorded | 6a13d77f6f71c5ae7dc9e7eb |
| ACE-SQL | 87.2 | Not recorded | 6a22586f86173ad9c1468975 |
| CHESS-SQL | 87.2 | Not recorded | 6a3b64a6206542251d7c9726 |
| OpenSearch-SQL+ GPT-4o | 87.1 | Not recorded | 6909886c3ef7ccd74e5e5946 |
| SuperSQL | 87 | Not recorded | 68fa76e01e209131cea6f8eb |
| N-Rep | 87 | Not recorded | 68fa78ab1e209131cea79c5f |
| JOLT-SQL | 86.8 | Not recorded | 6a22586f86173ad9c1468975 |
| PET-SQL | 86.7 | Not recorded | 68fa73661e209131cea5c396 |
| DAIL-SQL | 86.6 | Not recorded | 68fa7b801e209131cea88b5d |
| SENSE | 86.6 | Not recorded | 68fa7b801e209131cea88b5d |
| DAIL-SQL | 86.6 | Not recorded | 68fa73661e209131cea5c396 |
| DAIL-SQL + GPT-4 | 86.6 | Not recorded | 68fa75031e209131cea65402 |
| DAIL-SQL | 86.6 | Not recorded | 68fa76e01e209131cea6f8eb |
| DAIL-SQL + GPT-4 | 86.6 | Not recorded | 69608b6853fdd5c36174423d |
| DAIL-SQL | 86.6 | Not recorded | 68fa78ab1e209131cea79c5f |
| DAIL-SQL | 86.6 | Not recorded | 6a22586f86173ad9c1468975 |
| DAIL-SQL | 86.6 | Not recorded | 6a3b64a6206542251d7c9726 |
| SquRL-7B | 86.58 | Not recorded | 6995479009c33900fcd6d60c |
| KE-ICL | 86.4 | Not recorded | 6a13d77f6f71c5ae7dc9e7eb |
| DAIL-SQL | 86.2 | Not recorded | 68fa78961e209131cea79234 |
| CodeS | 86.16 | Not recorded | 6a13d77f6f71c5ae7dc9e7eb |
| EVOLSQL-Qwen-7B | 86.1 | Not recorded | 69608b6853fdd5c36174423d |
| KE-ICL | 85.98 | Not recorded | 6a13d77f6f71c5ae7dc9e7eb |
| Share | 85.9 | Not recorded | 6909886c3ef7ccd74e5e5946 |
| SQLForge-LM | 85.8 | Not recorded | 68fa7b801e209131cea88b5d |
| CodeS | 85.61 | Not recorded | 6a13d77f6f71c5ae7dc9e7eb |
| DPG-SQL | 85.6 | Not recorded | 68fa76e01e209131cea6f8eb |
| Tool-SQL | 85.6 | Not recorded | 68fa76e01e209131cea6f8eb |
| Think2SQL-14B | 85.6 | Not recorded | 68fa78481e209131cea7799a |
| Reward-SQL | 85.4 | Not recorded | 68fa78961e209131cea79234 |
| SQL-GEN | 85.32 | Not recorded | 6a13d77f6f71c5ae7dc9e7eb |
| DIN-SQL | 85.3 | Not recorded | 68fa7b801e209131cea88b5d |
| DIN-SQL + GPT-4 | 85.3 | Not recorded | 68fa710d1e209131cea4ee41 |
| DIN-SQL | 85.3 | Not recorded | 68fa73661e209131cea5c396 |
| DIN-SQL + GPT-4 | 85.3 | Not recorded | 68fa75031e209131cea65402 |
| DIN-SQL | 85.3 | Not recorded | 68fa76e01e209131cea6f8eb |
| DIN-SQL + GPT-4 | 85.3 | Not recorded | 69608b6853fdd5c36174423d |
| DIN-SQL | 85.3 | Not recorded | 6a22586f86173ad9c1468975 |
| DIN-SQL | 85.3 | Not recorded | 68fa78961e209131cea79234 |
| Omni | 85.14 | Not recorded | 6a13d77f6f71c5ae7dc9e7eb |
| SQL-o1 | 85.1 | Not recorded | 68fa78961e209131cea79234 |
| ROUTE | 85.1 | Not recorded | 6a3b64a6206542251d7c9726 |

### MiniSeek

Execution Accuracy: 91.2. Result ID: 69f1b3c747f34ce924d7d7fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78ab1e209131cea79c5f.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MARS-SQL

Execution Accuracy: 89.75. Result ID: 6a030ad547f34ce924e6bcfc.

[Reporting paper](<https://www.sota2.com/research/paper/6909886c3ef7ccd74e5e5946.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6909886c3ef7ccd74e5e5946.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MARS-SQL

Execution Accuracy: 89.75. Result ID: 6a030ad547f34ce924e6bd22.

[Reporting paper](<https://www.sota2.com/research/paper/6909886c3ef7ccd74e5e5946.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6909886c3ef7ccd74e5e5946.md>)

Recorded evaluation configuration: {"Size":"7B each","# agents":"3","Thinking?":"Yes","Training set":"Bird"}. This record does not assert independent reproduction.

### XiYan-SQL

Execution Accuracy: 89.65. Result ID: 69944fd63a6c3148491c6f29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76e01e209131cea6f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76e01e209131cea6f8eb.md>)

[Implementation](<https://github.com/XGenerationLab/XiYan-SQL>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### XiYan-SQL

Execution Accuracy: 89.65. Result ID: 6a030ad547f34ce924e6bd1b.

[Reporting paper](<https://www.sota2.com/research/paper/6909886c3ef7ccd74e5e5946.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d61e209131cea7fa43.md>)

Recorded evaluation configuration: {"# agents":"3","Thinking?":"No"}. This record does not assert independent reproduction.

### MCS-SQL + GPT-4

Execution Accuracy: 89.6. Result ID: 69936ec03a6c31484915e74e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75031e209131cea65402.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b0e0.md>)

Recorded evaluation configuration: {"Training with Spider":false}. This record does not assert independent reproduction.

### MCS-SQL

Execution Accuracy: 89.6. Result ID: 69944fd63a6c3148491c6f1f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76e01e209131cea6f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e51e209131cea6a84f.md>)

[Implementation](<https://github.com/ShayanTalaei/CHESS>)

Recorded evaluation configuration: {"backbone":"GPT-4"}. This record does not assert independent reproduction.

### MCS-SQL + GPT-4

Execution Accuracy: 89.6. Result ID: 699697085698665ec4e087e1.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6853fdd5c36174423d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b0e0.md>)

Recorded evaluation configuration: {"# Samples":"-","Method Type":"Prompting with Proprietary LLMs"}. This record does not assert independent reproduction.

### MCS-SQL

Execution Accuracy: 89.6. Result ID: 6a2293a5fbc373592c20f0b7.

[Reporting paper](<https://www.sota2.com/research/paper/6a22586f86173ad9c1468975.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b0e0.md>)

Recorded evaluation configuration: {"Base Model":"GPT-4"}. This record does not assert independent reproduction.

### MCS-SQL

Execution Accuracy: 89.6. Result ID: 6a3b82b5fbc373592c434ad6.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b0e0.md>)

Recorded evaluation configuration: {"Base Model":"GPT-4","Method Category":"Prompt-based"}. This record does not assert independent reproduction.

### Gemini3-Pro

Execution Accuracy: 89.5. Result ID: 699e3f3b5698665ec4fc3db1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78481e209131cea7799a.md>)

Recorded evaluation configuration: {"Model Accessibility":"Closed-Source"}. This record does not assert independent reproduction.

### EXPO-SQL

Execution Accuracy: 89.5. Result ID: 6a3b82b5fbc373592c434adf.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-14B"}. This record does not assert independent reproduction.

### Arctic-SQL-R1

Execution Accuracy: 89.4. Result ID: 6a3b82b5fbc373592c434adc.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78de1e209131cea7aea3.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-14B","Method Category":"RL-based"}. This record does not assert independent reproduction.

### EXPO-SQL

Execution Accuracy: 89.1. Result ID: 6a3b82b5fbc373592c434ade.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-7B"}. This record does not assert independent reproduction.

### OmniSQL-7B

Execution Accuracy: 88.9. Result ID: 6a3b82b5fbc373592c434ad1.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79fe1e209131cea8081e.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-7B","Method Category":"SFT-based"}. This record does not assert independent reproduction.

### Arctic-Text2SQL-R1

Execution Accuracy: 88.8. Result ID: 6a030ad547f34ce924e6bd20.

[Reporting paper](<https://www.sota2.com/research/paper/6909886c3ef7ccd74e5e5946.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78de1e209131cea7aea3.md>)

Recorded evaluation configuration: {"Size":"32B","# agents":"1","Thinking?":"Yes","Training set":"Bird+Spider"}. This record does not assert independent reproduction.

### Arctic-SQL-R1

Execution Accuracy: 88.8. Result ID: 6a3b82b5fbc373592c434adb.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78de1e209131cea7aea3.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-7B","Method Category":"RL-based"}. This record does not assert independent reproduction.

### SQL-R1

Execution Accuracy: 88.7. Result ID: 6a2293a5fbc373592c20f0bd.

[Reporting paper](<https://www.sota2.com/research/paper/6a22586f86173ad9c1468975.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c001e209131cea8bd16.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-7B"}. This record does not assert independent reproduction.

### SQL-R1

Execution Accuracy: 88.7. Result ID: 6a3b82b5fbc373592c434ad9.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c001e209131cea8bd16.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-7B","Method Category":"RL-based"}. This record does not assert independent reproduction.

### KE-ICL

Execution Accuracy: 88.68. Result ID: 6a13f7b0fbc373592c0ab96d.

[Reporting paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

Recorded evaluation configuration: {"LLM":"Gemini-Pro-1.5"}. This record does not assert independent reproduction.

### CodeS

Execution Accuracy: 88.31. Result ID: 6a13f7b0fbc373592c0ab96c.

[Reporting paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

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

Recorded evaluation configuration: {"LLM":"Gemini-Pro-1.5","Setting":"ICL"}. This record does not assert independent reproduction.

### SQL-R1

Execution Accuracy: 88.1. Result ID: 6a3b82b5fbc373592c434ada.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c001e209131cea8bd16.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-14B","Method Category":"RL-based"}. This record does not assert independent reproduction.

### KE-RL

Execution Accuracy: 87.97. Result ID: 6a13f7b0fbc373592c0ab97f.

[Reporting paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

Recorded evaluation configuration: {"LLM":"Qwen2.5-Coder-7B"}. This record does not assert independent reproduction.

### OmniSQL-7B

Execution Accuracy: 87.9. Result ID: 699697085698665ec4e087ee.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6853fdd5c36174423d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79fe1e209131cea8081e.md>)

Recorded evaluation configuration: {"# Samples":"2.5M","Method Type":"Fine-Tuning with Open-Source LLMs"}. This record does not assert independent reproduction.

### BASE-SQL

Execution Accuracy: 87.9. Result ID: 6a2293a5fbc373592c20f0be.

[Reporting paper](<https://www.sota2.com/research/paper/6a22586f86173ad9c1468975.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76fd1e209131cea70427.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-14B"}. This record does not assert independent reproduction.

### OmniSQL

Execution Accuracy: 87.9. Result ID: 6a2293a5fbc373592c20f0bf.

[Reporting paper](<https://www.sota2.com/research/paper/6a22586f86173ad9c1468975.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79fe1e209131cea8081e.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-7B"}. This record does not assert independent reproduction.

### CHASE-SQL

Execution Accuracy: 87.6. Result ID: 698c5a4f37894ef7d9cdc59e.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa75031e209131cea65402.md>)

Recorded evaluation configuration: {"Base":"Gemini-1.5","Size":"-","Multiple calls":true}. This record does not assert independent reproduction.

### PET-SQL

Execution Accuracy: 87.6. Result ID: 6992c6923a6c314849116af1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73661e209131cea5c396.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73661e209131cea5c396.md>)

[Implementation](<https://github.com/zhshLii/PETSQL>)

Recorded evaluation configuration: {"voting\_strategy":"Difficulty-aware voting"}. This record does not assert independent reproduction.

### CHASE-SQL + Gemini 1.5

Execution Accuracy: 87.6. Result ID: 69936ec03a6c31484915e74f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75031e209131cea65402.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75031e209131cea65402.md>)

Recorded evaluation configuration: {"Training with Spider":false}. This record does not assert independent reproduction.

### CHASE-SQL

Execution Accuracy: 87.6. Result ID: 69944fd63a6c3148491c6f20.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76e01e209131cea6f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75031e209131cea65402.md>)

Recorded evaluation configuration: {"backbone":"Gemini 1.5"}. This record does not assert independent reproduction.

### PET-SQL

Execution Accuracy: 87.6. Result ID: 69944fd63a6c3148491c6f21.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76e01e209131cea6f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73661e209131cea5c396.md>)

[Implementation](<https://github.com/zhshLii/PETSQL>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CHASE-SQL + Gemini

Execution Accuracy: 87.6. Result ID: 6a030ad547f34ce924e6bd1c.

[Reporting paper](<https://www.sota2.com/research/paper/6909886c3ef7ccd74e5e5946.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75031e209131cea65402.md>)

Recorded evaluation configuration: {"# agents":"4","Thinking?":"Yes"}. This record does not assert independent reproduction.

### OmniSQL

Execution Accuracy: 87.6. Result ID: 6a030ad547f34ce924e6bd1f.

[Reporting paper](<https://www.sota2.com/research/paper/6909886c3ef7ccd74e5e5946.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79fe1e209131cea8081e.md>)

Recorded evaluation configuration: {"Size":"32B","# agents":"1","Thinking?":"No","Training set":"OmniSQL"}. This record does not assert independent reproduction.

### CHASE-SQL

Execution Accuracy: 87.6. Result ID: 6a3b82b5fbc373592c434ad7.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75031e209131cea65402.md>)

Recorded evaluation configuration: {"Base Model":"Gemini-1.5-Pro","Method Category":"Prompt-based"}. This record does not assert independent reproduction.

### SQLForge-LM

Execution Accuracy: 87.4. Result ID: 698c5a4f37894ef7d9cdc5a7.

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

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

Recorded evaluation configuration: {"Base":"CodeLlama","Size":"13B","Multiple calls":false}. This record does not assert independent reproduction.

### CHESS

Execution Accuracy: 87.2. Result ID: 69936ec03a6c31484915e750.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75031e209131cea65402.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e51e209131cea6a84f.md>)

[Implementation](<https://github.com/ShayanTalaei/CHESS>)

Recorded evaluation configuration: {"Training with Spider":false}. This record does not assert independent reproduction.

### CHESS

Execution Accuracy: 87.2. Result ID: 69f1b3c747f34ce924d7d7fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78ab1e209131cea79c5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e51e209131cea6a84f.md>)

[Implementation](<https://github.com/ShayanTalaei/CHESS>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CHESS

Execution Accuracy: 87.2. Result ID: 6a030ad547f34ce924e6bd19.

[Reporting paper](<https://www.sota2.com/research/paper/6909886c3ef7ccd74e5e5946.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e51e209131cea6a84f.md>)

[Implementation](<https://github.com/ShayanTalaei/CHESS>)

Recorded evaluation configuration: {"# agents":"4","Thinking?":"No"}. This record does not assert independent reproduction.

### DAIL-SQL

Execution Accuracy: 87.2. Result ID: 6a13f7b0fbc373592c0ab96b.

[Reporting paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71411e209131cea502b9.md>)

Recorded evaluation configuration: {"LLM":"Gemini-Pro-1.5","Setting":"ICL"}. This record does not assert independent reproduction.

### ACE-SQL

Execution Accuracy: 87.2. Result ID: 6a2293a5fbc373592c20f0c1.

[Reporting paper](<https://www.sota2.com/research/paper/6a22586f86173ad9c1468975.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22586f86173ad9c1468975.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-8B"}. This record does not assert independent reproduction.

### CHESS-SQL

Execution Accuracy: 87.2. Result ID: 6a3b82b5fbc373592c434ad8.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e51e209131cea6a84f.md>)

[Implementation](<https://github.com/ShayanTalaei/CHESS>)

Recorded evaluation configuration: {"Base Model":"Deepseek-33B","Method Category":"Prompt-based"}. This record does not assert independent reproduction.

### OpenSearch-SQL+ GPT-4o

Execution Accuracy: 87.1. Result ID: 6a030ad547f34ce924e6bd1a.

[Reporting paper](<https://www.sota2.com/research/paper/6909886c3ef7ccd74e5e5946.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770b1e209131cea70b93.md>)

Recorded evaluation configuration: {"# agents":"4","Thinking?":"No"}. This record does not assert independent reproduction.

### SuperSQL

Execution Accuracy: 87. Result ID: 69944fd63a6c3148491c6f22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76e01e209131cea6f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74451e209131cea60a95.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### N-Rep

Execution Accuracy: 87. Result ID: 69f1b3c747f34ce924d7d7fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78ab1e209131cea79c5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78ab1e209131cea79c5f.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### JOLT-SQL

Execution Accuracy: 86.8. Result ID: 6a2293a5fbc373592c20f0bb.

[Reporting paper](<https://www.sota2.com/research/paper/6a22586f86173ad9c1468975.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b8a1e209131cea89054.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-7B"}. This record does not assert independent reproduction.

### PET-SQL

Execution Accuracy: 86.7. Result ID: 6992c6923a6c314849116af0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73661e209131cea5c396.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73661e209131cea5c396.md>)

[Implementation](<https://github.com/zhshLii/PETSQL>)

Recorded evaluation configuration: {"voting\_strategy":"Naive voting"}. This record does not assert independent reproduction.

### DAIL-SQL

Execution Accuracy: 86.6. Result ID: 698c5a4f37894ef7d9cdc59f.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa71411e209131cea502b9.md>)

Recorded evaluation configuration: {"Base":"GPT-4","Size":"-","Multiple calls":true}. This record does not assert independent reproduction.

### SENSE

Execution Accuracy: 86.6. Result ID: 698c5a4f37894ef7d9cdc5a3.

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

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

Recorded evaluation configuration: {"Base":"CodeLlama","Size":"13B","Multiple calls":false}. This record does not assert independent reproduction.

### DAIL-SQL

Execution Accuracy: 86.6. Result ID: 6992c6923a6c314849116aef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73661e209131cea5c396.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71411e209131cea502b9.md>)

Recorded evaluation configuration: {"backbone":"GPT-4","strategy":"Self-consistency"}. This record does not assert independent reproduction.

### DAIL-SQL + GPT-4

Execution Accuracy: 86.6. Result ID: 69936ec03a6c31484915e751.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75031e209131cea65402.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71411e209131cea502b9.md>)

Recorded evaluation configuration: {"Training with Spider":true}. This record does not assert independent reproduction.

### DAIL-SQL

Execution Accuracy: 86.6. Result ID: 69944fd63a6c3148491c6f23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76e01e209131cea6f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71411e209131cea502b9.md>)

Recorded evaluation configuration: {"backbone":"GPT-4"}. This record does not assert independent reproduction.

### DAIL-SQL + GPT-4

Execution Accuracy: 86.6. Result ID: 699697085698665ec4e087df.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6853fdd5c36174423d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71411e209131cea502b9.md>)

Recorded evaluation configuration: {"# Samples":"-","Method Type":"Prompting with Proprietary LLMs"}. This record does not assert independent reproduction.

### DAIL-SQL

Execution Accuracy: 86.6. Result ID: 69f1b3c747f34ce924d7d7fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78ab1e209131cea79c5f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71411e209131cea502b9.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DAIL-SQL

Execution Accuracy: 86.6. Result ID: 6a2293a5fbc373592c20f0b5.

[Reporting paper](<https://www.sota2.com/research/paper/6a22586f86173ad9c1468975.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71411e209131cea502b9.md>)

Recorded evaluation configuration: {"Base Model":"GPT-4"}. This record does not assert independent reproduction.

### DAIL-SQL

Execution Accuracy: 86.6. Result ID: 6a3b82b5fbc373592c434ad5.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71411e209131cea502b9.md>)

Recorded evaluation configuration: {"Base Model":"GPT-4","Method Category":"Prompt-based"}. This record does not assert independent reproduction.

### SquRL-7B

Execution Accuracy: 86.58. Result ID: 699ad9ae5698665ec4692c35.

[Reporting paper](<https://www.sota2.com/research/paper/6995479009c33900fcd6d60c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6995479009c33900fcd6d60c.md>)

Recorded evaluation configuration: {"workflow":"dynamic","number of workflows":"5","aggregation":"majority voting","parameter scale":"7B"}. This record does not assert independent reproduction.

### KE-ICL

Execution Accuracy: 86.4. Result ID: 6a13f7b0fbc373592c0ab96a.

[Reporting paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

Recorded evaluation configuration: {"LLM":"GPT-4o"}. This record does not assert independent reproduction.

### DAIL-SQL

Execution Accuracy: 86.2. Result ID: 6a2f9abafbc373592c2b282c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78961e209131cea79234.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71411e209131cea502b9.md>)

Recorded evaluation configuration: {"Category":"Prompting-based Methods","Base Model":"GPT-4"}. This record does not assert independent reproduction.

### CodeS

Execution Accuracy: 86.16. Result ID: 6a13f7b0fbc373592c0ab969.

[Reporting paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

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

Recorded evaluation configuration: {"LLM":"GPT-4o","Setting":"ICL"}. This record does not assert independent reproduction.

### EVOLSQL-Qwen-7B

Execution Accuracy: 86.1. Result ID: 699697085698665ec4e087f1.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6853fdd5c36174423d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69608b6853fdd5c36174423d.md>)

Recorded evaluation configuration: {"# Samples":"140K","Method Type":"Fine-Tuning with Open-Source LLMs"}. This record does not assert independent reproduction.

### KE-ICL

Execution Accuracy: 85.98. Result ID: 6a13f7b0fbc373592c0ab97c.

[Reporting paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

Recorded evaluation configuration: {"LLM":"Qwen2.5-Coder-7B"}. This record does not assert independent reproduction.

### Share

Execution Accuracy: 85.9. Result ID: 6a030ad547f34ce924e6bd1e.

[Reporting paper](<https://www.sota2.com/research/paper/6909886c3ef7ccd74e5e5946.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78fc1e209131cea7b7a6.md>)

Recorded evaluation configuration: {"Size":"8B","# agents":"1","Thinking?":"No","Training set":"Bird"}. This record does not assert independent reproduction.

### SQLForge-LM

Execution Accuracy: 85.8. Result ID: 698c5a4f37894ef7d9cdc5a6.

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

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

Recorded evaluation configuration: {"Base":"CodeLlama","Size":"7B","Multiple calls":false}. This record does not assert independent reproduction.

### CodeS

Execution Accuracy: 85.61. Result ID: 6a13f7b0fbc373592c0ab97b.

[Reporting paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

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

Recorded evaluation configuration: {"LLM":"Qwen2.5-Coder-7B","Setting":"ICL"}. This record does not assert independent reproduction.

### DPG-SQL

Execution Accuracy: 85.6. Result ID: 69944fd63a6c3148491c6f24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76e01e209131cea6f8eb.md>)

Recorded evaluation configuration: {"backbone":"GPT-4"}. This record does not assert independent reproduction.

### Tool-SQL

Execution Accuracy: 85.6. Result ID: 69944fd63a6c3148491c6f25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76e01e209131cea6f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a21e209131cea62d02.md>)

Recorded evaluation configuration: {"backbone":"GPT-4"}. This record does not assert independent reproduction.

### Think2SQL-14B

Execution Accuracy: 85.6. Result ID: 699e3f3b5698665ec4fc3db0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78481e209131cea7799a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78481e209131cea7799a.md>)

Recorded evaluation configuration: {"Model Scale Category":"10-50B","Model Accessibility":"Open-source"}. This record does not assert independent reproduction.

### Reward-SQL

Execution Accuracy: 85.4. Result ID: 6a2f9abafbc373592c2b2836.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78961e209131cea79234.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78961e209131cea79234.md>)

Recorded evaluation configuration: {"Category":"Our Approach","Base Model":"Qwen3-8B","Decoding Strategy":"PRM@32 (Best-of-N)"}. This record does not assert independent reproduction.

### SQL-GEN

Execution Accuracy: 85.32. Result ID: 6a13f7b0fbc373592c0ab97d.

[Reporting paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75031e209131cea653cf.md>)

Recorded evaluation configuration: {"LLM":"Qwen2.5-Coder-7B","Setting":"RL"}. This record does not assert independent reproduction.

### DIN-SQL

Execution Accuracy: 85.3. Result ID: 698c5a4f37894ef7d9cdc5a0.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa710d1e209131cea4ee41.md>)

[Implementation](<https://github.com/MohammadrezaPourreza/Few-shot-NL2SQL-with-prompting>)

Recorded evaluation configuration: {"Base":"GPT-4","Size":"-","Multiple calls":true}. This record does not assert independent reproduction.

### DIN-SQL + GPT-4

Execution Accuracy: 85.3. Result ID: 6991786c3a6c314849085bc6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa710d1e209131cea4ee41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710d1e209131cea4ee41.md>)

[Implementation](<https://github.com/MohammadrezaPourreza/Few-shot-NL2SQL-with-prompting>)

Recorded evaluation configuration: {"Backbone":"GPT-4"}. This record does not assert independent reproduction.

### DIN-SQL

Execution Accuracy: 85.3. Result ID: 6992c6923a6c314849116aee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73661e209131cea5c396.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710d1e209131cea4ee41.md>)

[Implementation](<https://github.com/MohammadrezaPourreza/Few-shot-NL2SQL-with-prompting>)

Recorded evaluation configuration: {"backbone":"GPT-4"}. This record does not assert independent reproduction.

### DIN-SQL + GPT-4

Execution Accuracy: 85.3. Result ID: 69936ec03a6c31484915e752.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75031e209131cea65402.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710d1e209131cea4ee41.md>)

[Implementation](<https://github.com/MohammadrezaPourreza/Few-shot-NL2SQL-with-prompting>)

Recorded evaluation configuration: {"Training with Spider":true}. This record does not assert independent reproduction.

### DIN-SQL

Execution Accuracy: 85.3. Result ID: 69944fd63a6c3148491c6f26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76e01e209131cea6f8eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710d1e209131cea4ee41.md>)

[Implementation](<https://github.com/MohammadrezaPourreza/Few-shot-NL2SQL-with-prompting>)

Recorded evaluation configuration: {"backbone":"GPT-4"}. This record does not assert independent reproduction.

### DIN-SQL + GPT-4

Execution Accuracy: 85.3. Result ID: 699697085698665ec4e087de.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6853fdd5c36174423d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710d1e209131cea4ee41.md>)

[Implementation](<https://github.com/MohammadrezaPourreza/Few-shot-NL2SQL-with-prompting>)

Recorded evaluation configuration: {"# Samples":"-","Method Type":"Prompting with Proprietary LLMs"}. This record does not assert independent reproduction.

### DIN-SQL

Execution Accuracy: 85.3. Result ID: 6a2293a5fbc373592c20f0b4.

[Reporting paper](<https://www.sota2.com/research/paper/6a22586f86173ad9c1468975.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710d1e209131cea4ee41.md>)

[Implementation](<https://github.com/MohammadrezaPourreza/Few-shot-NL2SQL-with-prompting>)

Recorded evaluation configuration: {"Base Model":"GPT-4"}. This record does not assert independent reproduction.

### DIN-SQL

Execution Accuracy: 85.3. Result ID: 6a2f9abafbc373592c2b282b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78961e209131cea79234.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa710d1e209131cea4ee41.md>)

[Implementation](<https://github.com/MohammadrezaPourreza/Few-shot-NL2SQL-with-prompting>)

Recorded evaluation configuration: {"Category":"Prompting-based Methods","Base Model":"GPT-4"}. This record does not assert independent reproduction.

### Omni

Execution Accuracy: 85.14. Result ID: 6a13f7b0fbc373592c0ab97e.

[Reporting paper](<https://www.sota2.com/research/paper/6a13d77f6f71c5ae7dc9e7eb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79fe1e209131cea8081e.md>)

Recorded evaluation configuration: {"LLM":"Qwen2.5-Coder-7B","Setting":"RL"}. This record does not assert independent reproduction.

### SQL-o1

Execution Accuracy: 85.1. Result ID: 6a2f9abafbc373592c2b282f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78961e209131cea79234.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78bc1e209131cea7a20c.md>)

Recorded evaluation configuration: {"Category":"Supervised Fine-tuning Methods","Base Model":"Qwen2.5-7B","Decoding Strategy":"Vote@N"}. This record does not assert independent reproduction.

### ROUTE

Execution Accuracy: 85.1. Result ID: 6a3b82b5fbc373592c434ad2.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64a6206542251d7c9726.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c41e209131cea7a63b.md>)

Recorded evaluation configuration: {"Base Model":"Qwen2.5-Coder-7B","Method Category":"SFT-based"}. This record does not assert independent reproduction.

Page 1 of 4. This is an index page, not the full collection.

- [Next index page](<https://www.sota2.com/research/sota/text-to-sql-on-spider-test.md?metric=Execution%20Accuracy&page=2>): Follow this link to discover more pages.
