# Program Evolution on LLM-SQL

Source: [Program Evolution on LLM-SQL](<https://www.sota2.com/research/sota/program-evolution-on-llm-sql>)

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

Data updated: 2026-06-16T08:53:43.535Z

Evaluation of model performance on the LLM-SQL dataset focusing on Program Evolution capabilities, measured by Score, Correctness, Scalability (Time/Memory), and Optimality.

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 | Program Evolution |
| Dataset (including any stated split) | LLM-SQL |
| Metric | Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Score](<https://www.sota2.com/research/sota/program-evolution-on-llm-sql.md?metric=Score>): Higher is better; unit: SCALAR.

- [Correctness](<https://www.sota2.com/research/sota/program-evolution-on-llm-sql.md?metric=Correctness>): Higher is better; unit: PERCENT.

- [Scalability Time](<https://www.sota2.com/research/sota/program-evolution-on-llm-sql.md?metric=Scalability%20Time>): Lower is better; unit: TIME.

- [Scalability Memory](<https://www.sota2.com/research/sota/program-evolution-on-llm-sql.md?metric=Scalability%20Memory>): Lower is better; unit: SIZE.

- [Optimality Score](<https://www.sota2.com/research/sota/program-evolution-on-llm-sql.md?metric=Optimality%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| AdaEvolve+Prompt fixing | 0.734 | Not recorded | 6a30d8a5d33dfb23e783ccea |
| AdaEvolve (reproduced) | 0.73 | Not recorded | 6a30d8a5d33dfb23e783ccea |
| AdaEvolve+AICHILLES | 0.712 | Not recorded | 6a30d8a5d33dfb23e783ccea |
| Human baseline | 0.692 | Not recorded | 6a30d8a5d33dfb23e783ccea |

### AdaEvolve+Prompt fixing

Score: 0.734. Result ID: 6a310f04fbc373592c2d7b96.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d8a5d33dfb23e783ccea.md>)

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

### AdaEvolve (reproduced)

Score: 0.73. Result ID: 6a310f04fbc373592c2d7b95.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d8a5d33dfb23e783ccea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699d30ca6017c4460ffab84b.md>)

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

### AdaEvolve+AICHILLES

Score: 0.712. Result ID: 6a310f04fbc373592c2d7b97.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d8a5d33dfb23e783ccea.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a30d8a5d33dfb23e783ccea.md>)

Recorded evaluation configuration: {"AICHILLES iterations":"100"}. This record does not assert independent reproduction.

### Human baseline

Score: 0.692. Result ID: 6a310f04fbc373592c2d7b94.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d8a5d33dfb23e783ccea.md>)

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

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