Complex Reasoning on Structured Data on WikiSQL-E
85.6DACRAFTQA
Evaluation Results
| Method | Links | |
|---|---|---|
| CRAFTQAInference Engine=GPT-4o, Model Source Type=Closed-source Models2026.06 | 85.6 | |
| TrustUQAInference Engine=GPT-4o2026.06 | 80.1 | |
| CRAFTQAInference Engine=GPT-4o-mini, Model Source Type=Closed-source Models2026.06 | 79 | |
| CRAFTQAInference Engine=LLaMA-3.1-8B, Model Source Type=Open-source Models2026.06 | 76 | |
| TrustUQAInference Engine=GPT-4o-mini2026.06 | 74.5 | |
| TrustUQAInference Engine=GPT-3.5-Turbo2026.06 | 70 | |
| CRAFTQAInference Engine=GPT-3.5-Turbo, Model Source Type=Closed-source Models2026.06 | 67.8 | |
| CRAFTQAInference Engine=Qwen2.5-7B, Model Source Type=Open-source Models2026.06 | 65.9 | |
| ReadiInference Engine=GPT-4o2026.06 | 51.3 | |
| ReadiInference Engine=GPT-3.5-Turbo2026.06 | 45.1 | |
| StructGPTInference Engine=GPT-3.5-Turbo2026.06 | 44 | |
| StructGPTInference Engine=GPT-4o2026.06 | 43.5 | |
| StructGPTInference Engine=GPT-4o-mini2026.06 | 38.8 | |
| ReadiInference Engine=GPT-4o-mini2026.06 | 37.5 | |
| PoTInference Engine=GPT-4o2026.06 | 27.4 | |
| PoTInference Engine=GPT-3.5-Turbo2026.06 | 25 | |
| PoTInference Engine=GPT-4o-mini2026.06 | 25 |