List your company

Dataset-level accuracy estimation on Spider to BIRD

3.1MAEFusionSQL
2.3567.37812.417.422Mar 8, 2026

Evaluation results

MethodLinks
FusionSQLModel=Qwen2.5-72B2026.033.1
FusionSQL-TLModel=Qwen2.5-72B2026.033.4
FusionSQLModel=Llama-3.1-70B2026.033.7
FusionSQL-TLModel=Llama-3.1-70B2026.034
FusionSQLModel=DeepSeek-33B2026.034.2
FusionSQLModel=Avg.2026.034.2
FusionSQL-TLModel=DeepSeek-33B2026.034.6
FusionSQL-TLModel=Avg.2026.034.6
FusionSQLModel=XiYanSQL-14B2026.034.8
FusionSQLModel=CSC-SQL-7B2026.035.1
FusionSQL-TLModel=XiYanSQL-14B2026.035.2
FusionSQL-TLModel=CSC-SQL-7B2026.035.6
ArenaCmpModel=Qwen2.5-72B2026.039.7
ArenaCmpModel=Llama-3.1-70B2026.0310.4
ArenaCmpModel=DeepSeek-33B2026.0311.2
ArenaCmpModel=Avg.2026.0311.5
PseAutoEvalModel=Qwen2.5-72B2026.0311.6
PseAutoEvalModel=Llama-3.1-70B2026.0312.2
ArenaCmpModel=XiYanSQL-14B2026.0312.6
PseAutoEvalModel=DeepSeek-33B2026.0313.1
ArenaCmpModel=CSC-SQL-7B2026.0313.5
PseAutoEvalModel=Avg.2026.0313.7
ATC-MCModel=Qwen2.5-72B2026.0313.9
ATC-MCModel=Llama-3.1-70B2026.0314.6
BugJudgeModel=Qwen2.5-72B2026.0314.8
ATC-NEModel=Qwen2.5-72B2026.0315
PseAutoEvalModel=XiYanSQL-14B2026.0315.1
ATC-MCModel=DeepSeek-33B2026.0315.2
BugJudgeModel=Llama-3.1-70B2026.0315.4
DoC (τ=0.8)Model=Qwen2.5-72B2026.0315.5
ATC-NEModel=Llama-3.1-70B2026.0315.7
ATC-MCModel=Avg.2026.0315.9
DoC (τ=0.8)Model=Llama-3.1-70B2026.0316
BugJudgeModel=DeepSeek-33B2026.0316.2
PseAutoEvalModel=CSC-SQL-7B2026.0316.3
ATC-NEModel=DeepSeek-33B2026.0316.5
DoC (τ=0.9)Model=Qwen2.5-72B2026.0316.7
BugJudgeModel=Avg.2026.0316.7
ATC-NEModel=Avg.2026.0317.1
DoC (τ=0.8)Model=DeepSeek-33B2026.0317.3
DoC (τ=0.9)Model=Llama-3.1-70B2026.0317.3
ATC-MCModel=XiYanSQL-14B2026.0317.4
DoC (τ=0.8)Model=Avg.2026.0317.7
BugJudgeModel=XiYanSQL-14B2026.0318.1
ATC-MCModel=CSC-SQL-7B2026.0318.3
ATC-NEModel=XiYanSQL-14B2026.0318.6
DoC (τ=0.9)Model=DeepSeek-33B2026.0318.6
DoC (τ=0.9)Model=Avg.2026.0318.9
BugJudgeModel=CSC-SQL-7B2026.0319
DoC (τ=0.8)Model=XiYanSQL-14B2026.0319.2
ATC-NEModel=CSC-SQL-7B2026.0319.8
DoC (τ=0.9)Model=XiYanSQL-14B2026.0320.3
DoC (τ=0.8)Model=CSC-SQL-7B2026.0320.5
DoC (τ=0.9)Model=CSC-SQL-7B2026.0321.7