Dataset-level accuracy estimation on Spider to BIRD
3.1MAEFusionSQL
Evaluation Results
| Method | Links | |
|---|---|---|
| FusionSQLModel=Qwen2.5-72B2026.03 | 3.1 | |
| FusionSQL-TLModel=Qwen2.5-72B2026.03 | 3.4 | |
| FusionSQLModel=Llama-3.1-70B2026.03 | 3.7 | |
| FusionSQL-TLModel=Llama-3.1-70B2026.03 | 4 | |
| FusionSQLModel=DeepSeek-33B2026.03 | 4.2 | |
| FusionSQLModel=Avg.2026.03 | 4.2 | |
| FusionSQL-TLModel=DeepSeek-33B2026.03 | 4.6 | |
| FusionSQL-TLModel=Avg.2026.03 | 4.6 | |
| FusionSQLModel=XiYanSQL-14B2026.03 | 4.8 | |
| FusionSQLModel=CSC-SQL-7B2026.03 | 5.1 | |
| FusionSQL-TLModel=XiYanSQL-14B2026.03 | 5.2 | |
| FusionSQL-TLModel=CSC-SQL-7B2026.03 | 5.6 | |
| ArenaCmpModel=Qwen2.5-72B2026.03 | 9.7 | |
| ArenaCmpModel=Llama-3.1-70B2026.03 | 10.4 | |
| ArenaCmpModel=DeepSeek-33B2026.03 | 11.2 | |
| ArenaCmpModel=Avg.2026.03 | 11.5 | |
| PseAutoEvalModel=Qwen2.5-72B2026.03 | 11.6 | |
| PseAutoEvalModel=Llama-3.1-70B2026.03 | 12.2 | |
| ArenaCmpModel=XiYanSQL-14B2026.03 | 12.6 | |
| PseAutoEvalModel=DeepSeek-33B2026.03 | 13.1 | |
| ArenaCmpModel=CSC-SQL-7B2026.03 | 13.5 | |
| PseAutoEvalModel=Avg.2026.03 | 13.7 | |
| ATC-MCModel=Qwen2.5-72B2026.03 | 13.9 | |
| ATC-MCModel=Llama-3.1-70B2026.03 | 14.6 | |
| BugJudgeModel=Qwen2.5-72B2026.03 | 14.8 | |
| ATC-NEModel=Qwen2.5-72B2026.03 | 15 | |
| PseAutoEvalModel=XiYanSQL-14B2026.03 | 15.1 | |
| ATC-MCModel=DeepSeek-33B2026.03 | 15.2 | |
| BugJudgeModel=Llama-3.1-70B2026.03 | 15.4 | |
| DoC (τ=0.8)Model=Qwen2.5-72B2026.03 | 15.5 | |
| ATC-NEModel=Llama-3.1-70B2026.03 | 15.7 | |
| ATC-MCModel=Avg.2026.03 | 15.9 | |
| DoC (τ=0.8)Model=Llama-3.1-70B2026.03 | 16 | |
| BugJudgeModel=DeepSeek-33B2026.03 | 16.2 | |
| PseAutoEvalModel=CSC-SQL-7B2026.03 | 16.3 | |
| ATC-NEModel=DeepSeek-33B2026.03 | 16.5 | |
| DoC (τ=0.9)Model=Qwen2.5-72B2026.03 | 16.7 | |
| BugJudgeModel=Avg.2026.03 | 16.7 | |
| ATC-NEModel=Avg.2026.03 | 17.1 | |
| DoC (τ=0.8)Model=DeepSeek-33B2026.03 | 17.3 | |
| DoC (τ=0.9)Model=Llama-3.1-70B2026.03 | 17.3 | |
| ATC-MCModel=XiYanSQL-14B2026.03 | 17.4 | |
| DoC (τ=0.8)Model=Avg.2026.03 | 17.7 | |
| BugJudgeModel=XiYanSQL-14B2026.03 | 18.1 | |
| ATC-MCModel=CSC-SQL-7B2026.03 | 18.3 | |
| ATC-NEModel=XiYanSQL-14B2026.03 | 18.6 | |
| DoC (τ=0.9)Model=DeepSeek-33B2026.03 | 18.6 | |
| DoC (τ=0.9)Model=Avg.2026.03 | 18.9 | |
| BugJudgeModel=CSC-SQL-7B2026.03 | 19 | |
| DoC (τ=0.8)Model=XiYanSQL-14B2026.03 | 19.2 | |
| ATC-NEModel=CSC-SQL-7B2026.03 | 19.8 | |
| DoC (τ=0.9)Model=XiYanSQL-14B2026.03 | 20.3 | |
| DoC (τ=0.8)Model=CSC-SQL-7B2026.03 | 20.5 | |
| DoC (τ=0.9)Model=CSC-SQL-7B2026.03 | 21.7 |