List your company

Dataset-level accuracy estimation on WikiSQL to Spider 2.0

4.2MAEFusionSQL
3.3049.35215.421.448Mar 8, 2026

Evaluation results

MethodLinks
FusionSQLModel=Qwen2.5-72B2026.034.2
FusionSQL-TLModel=Qwen2.5-72B2026.034.5
FusionSQLModel=Llama-3.1-70B2026.034.8
FusionSQL-TLModel=Llama-3.1-70B2026.035.1
FusionSQLModel=DeepSeek-33B2026.035.3
FusionSQLModel=Avg.2026.035.3
FusionSQL-TLModel=DeepSeek-33B2026.035.6
FusionSQL-TLModel=Avg.2026.035.6
FusionSQLModel=XiYanSQL-14B2026.035.8
FusionSQL-TLModel=XiYanSQL-14B2026.036.1
FusionSQLModel=CSC-SQL-7B2026.036.3
FusionSQL-TLModel=CSC-SQL-7B2026.036.6
ArenaCmpModel=Qwen2.5-72B2026.0312.6
ArenaCmpModel=Llama-3.1-70B2026.0313.4
ArenaCmpModel=DeepSeek-33B2026.0314.5
ArenaCmpModel=Avg.2026.0314.6
ArenaCmpModel=XiYanSQL-14B2026.0315.8
PseAutoEvalModel=Qwen2.5-72B2026.0316.3
ArenaCmpModel=CSC-SQL-7B2026.0316.9
PseAutoEvalModel=Llama-3.1-70B2026.0317
BugJudgeModel=Qwen2.5-72B2026.0317.3
PseAutoEvalModel=DeepSeek-33B2026.0317.7
ATC-MCModel=Qwen2.5-72B2026.0318
PseAutoEvalModel=Avg.2026.0318
BugJudgeModel=Llama-3.1-70B2026.0318.1
ATC-MCModel=Llama-3.1-70B2026.0318.7
PseAutoEvalModel=XiYanSQL-14B2026.0318.8
BugJudgeModel=DeepSeek-33B2026.0319.3
ATC-NEModel=Qwen2.5-72B2026.0319.4
BugJudgeModel=Avg.2026.0319.5
ATC-MCModel=DeepSeek-33B2026.0319.6
ATC-MCModel=Avg.2026.0319.9
ATC-NEModel=Llama-3.1-70B2026.0320.1
PseAutoEvalModel=CSC-SQL-7B2026.0320.1
DoC (τ=0.8)Model=Qwen2.5-72B2026.0320.5
BugJudgeModel=XiYanSQL-14B2026.0320.7
ATC-MCModel=XiYanSQL-14B2026.0321
ATC-NEModel=DeepSeek-33B2026.0321.3
DoC (τ=0.8)Model=Llama-3.1-70B2026.0321.3
ATC-NEModel=Avg.2026.0321.5
DoC (τ=0.9)Model=Qwen2.5-72B2026.0321.7
BugJudgeModel=CSC-SQL-7B2026.0322
ATC-MCModel=CSC-SQL-7B2026.0322.2
DoC (τ=0.9)Model=Llama-3.1-70B2026.0322.5
ATC-NEModel=XiYanSQL-14B2026.0322.6
DoC (τ=0.8)Model=DeepSeek-33B2026.0322.7
DoC (τ=0.8)Model=Avg.2026.0322.8
ATC-NEModel=CSC-SQL-7B2026.0323.9
DoC (τ=0.9)Model=DeepSeek-33B2026.0323.9
DoC (τ=0.9)Model=Avg.2026.0323.9
DoC (τ=0.8)Model=XiYanSQL-14B2026.0324
DoC (τ=0.9)Model=XiYanSQL-14B2026.0325.2
DoC (τ=0.8)Model=CSC-SQL-7B2026.0325.4
DoC (τ=0.9)Model=CSC-SQL-7B2026.0326.6