List your company

Dataset-level accuracy estimation on SParC to CoSQL

1.5MAEFusionSQL-TL
1.1243.6626.28.738Mar 8, 2026

Evaluation results

MethodLinks
FusionSQL-TLModel=Qwen2.5-72B2026.031.5
FusionSQLModel=Qwen2.5-72B2026.031.6
FusionSQL-TLModel=Llama-3.1-70B2026.031.7
FusionSQLModel=Llama-3.1-70B2026.031.8
FusionSQL-TLModel=DeepSeek-33B2026.032
FusionSQL-TLModel=Avg.2026.032
FusionSQLModel=DeepSeek-33B2026.032.1
FusionSQLModel=Avg.2026.032.1
FusionSQL-TLModel=XiYanSQL-14B2026.032.2
FusionSQLModel=XiYanSQL-14B2026.032.3
FusionSQL-TLModel=CSC-SQL-7B2026.032.4
FusionSQLModel=CSC-SQL-7B2026.032.5
ArenaCmpModel=Qwen2.5-72B2026.033.9
ArenaCmpModel=Llama-3.1-70B2026.034.4
ArenaCmpModel=DeepSeek-33B2026.034.9
ArenaCmpModel=Avg.2026.034.9
ArenaCmpModel=XiYanSQL-14B2026.035.4
PseAutoEvalModel=Qwen2.5-72B2026.035.5
ArenaCmpModel=CSC-SQL-7B2026.035.9
PseAutoEvalModel=Llama-3.1-70B2026.036.1
BugJudgeModel=Qwen2.5-72B2026.036.1
ATC-MCModel=Qwen2.5-72B2026.036.5
PseAutoEvalModel=DeepSeek-33B2026.036.7
PseAutoEvalModel=Avg.2026.036.7
BugJudgeModel=Llama-3.1-70B2026.036.7
ATC-NEModel=Qwen2.5-72B2026.037.1
ATC-MCModel=Llama-3.1-70B2026.037.2
PseAutoEvalModel=XiYanSQL-14B2026.037.2
BugJudgeModel=DeepSeek-33B2026.037.3
BugJudgeModel=Avg.2026.037.3
DoC (τ=0.8)Model=Qwen2.5-72B2026.037.7
ATC-MCModel=DeepSeek-33B2026.037.8
ATC-MCModel=Avg.2026.037.8
ATC-NEModel=Llama-3.1-70B2026.037.8
PseAutoEvalModel=CSC-SQL-7B2026.037.8
BugJudgeModel=XiYanSQL-14B2026.037.9
ATC-MCModel=XiYanSQL-14B2026.038.3
DoC (τ=0.8)Model=Llama-3.1-70B2026.038.3
ATC-NEModel=DeepSeek-33B2026.038.4
ATC-NEModel=Avg.2026.038.4
BugJudgeModel=CSC-SQL-7B2026.038.4
DoC (τ=0.8)Model=DeepSeek-33B2026.038.8
DoC (τ=0.8)Model=Avg.2026.038.8
DoC (τ=0.9)Model=Qwen2.5-72B2026.038.8
ATC-MCModel=CSC-SQL-7B2026.039
ATC-NEModel=XiYanSQL-14B2026.039
DoC (τ=0.8)Model=XiYanSQL-14B2026.039.3
DoC (τ=0.9)Model=Llama-3.1-70B2026.039.3
ATC-NEModel=CSC-SQL-7B2026.039.6
DoC (τ=0.9)Model=DeepSeek-33B2026.039.8
DoC (τ=0.9)Model=Avg.2026.039.8
DoC (τ=0.8)Model=CSC-SQL-7B2026.039.9
DoC (τ=0.9)Model=XiYanSQL-14B2026.0310.4
DoC (τ=0.9)Model=CSC-SQL-7B2026.0310.9