SQL Execution Validation on MySQL
64.2MySQL Execution ScoreRADAGAS-GPT4o
Evaluation Results
| Method | Links | |
|---|---|---|
| RADAGAS-GPT4oLLM Backbone=GPT-4o2026.05 | 64.2 | |
| RADAGAS-DeepSeekLLM Backbone=DeepSeek2026.05 | 60.96 | |
| RADAGAS-ClaudeLLM Backbone=Claude2026.05 | 60.52 | |
| GenSQLi2026.05 | 36.96 | |
| RefleXQLi2026.05 | 27.8 | |
| Traditional2026.05 | 23.12 | |
| Vanilla GPT-4oLLM Backbone=GPT-4o2026.05 | 21.44 |