Text-to-SQL on Spider no-easy
61.4AccuracySFT
Evaluation Results
| Method | Links | |
|---|---|---|
| SFTModel=Qwen2.5-7B-Instruct, Evaluation Protocol=FULL2026.05 | 61.4 | |
| BaseModel=Qwen2.5-7B-Instruct, Evaluation Protocol=FULL2026.05 | 61.2 | |
| RLSTAModel=Qwen2.5-7B-Instruct, Evaluation Protocol=FULL2026.05 | 59.8 | |
| MAIGOModel=Qwen2.5-7B-Instruct, Evaluation Protocol=FULL2026.05 | 59.6 | |
| GRPOModel=Qwen2.5-7B-Instruct, Evaluation Protocol=FULL2026.05 | 59.4 | |
| RLSTAModel=Qwen2.5-3B-Instruct, Evaluation Protocol=FULL2026.05 | 52 | |
| MAIGOModel=Qwen2.5-3B-Instruct, Evaluation Protocol=FULL2026.05 | 51.9 | |
| GRPOModel=Qwen2.5-3B-Instruct, Evaluation Protocol=FULL2026.05 | 51.7 | |
| SFTModel=Qwen2.5-3B-Instruct, Evaluation Protocol=FULL2026.05 | 50.8 | |
| BaseModel=Qwen2.5-3B-Instruct, Evaluation Protocol=FULL2026.05 | 50.7 | |
| MAIGOModel=Qwen2.5-7B-Instruct, Evaluation Protocol=SHARDED2026.05 | 50 | |
| RLSTAModel=Qwen2.5-7B-Instruct, Evaluation Protocol=SHARDED2026.05 | 45 | |
| MAIGOModel=Qwen2.5-3B-Instruct, Evaluation Protocol=SHARDED2026.05 | 44.9 | |
| SFTModel=Qwen2.5-7B-Instruct, Evaluation Protocol=SHARDED2026.05 | 44.1 | |
| GRPOModel=Qwen2.5-7B-Instruct, Evaluation Protocol=SHARDED2026.05 | 42.5 | |
| BaseModel=Qwen2.5-7B-Instruct, Evaluation Protocol=SHARDED2026.05 | 42.2 | |
| RLSTAModel=Qwen2.5-3B-Instruct, Evaluation Protocol=SHARDED2026.05 | 37 | |
| SFTModel=Qwen2.5-3B-Instruct, Evaluation Protocol=SHARDED2026.05 | 36.6 | |
| GRPOModel=Qwen2.5-3B-Instruct, Evaluation Protocol=SHARDED2026.05 | 34 | |
| BaseModel=Qwen2.5-3B-Instruct, Evaluation Protocol=SHARDED2026.05 | 32.9 |