Share your thoughts, 1 month free Claude Pro on usSee more

Text-to-SQL on Spider-DK

76.8Gre Score

SQL-TRAIL

Updated 1mo ago

Evaluation Results

Method
SQL-TRAIL 2026.01	76.8	-	-	-	-	-	78.1	-
SQL-Trail-7B 2026.03	76.8	-	-	-	-	-	77.8	-
Omini-SQL 2026.01	76.1	-	-	-	-	-	77.8	-
SynSQL(2.5M) 2025.12	76.1	-	-	-	-	-	77.8	-
OmniSQL-7B 2026.03	76.1	-	-	-	-	-	77.8	-
Reasoning-SQL 2026.01	73.3	-	-	-	-	-	-	-
GPT-4o-mini 2025.12	73.3	-	-	-	-	-	74.4	-
GPT-4o 2025.12	72.9	-	-	-	-	-	73.5	-
MTIR-SQL-8B 2026.03	72.9	-	-	-	-	-	-	-
GPT-4-Turbo 2025.12	72.3	-	-	-	-	-	72.1	-
SynSQL(2.5M) 2025.12	72.3	-	-	-	-	-	74.7	-
TRUST-SQL-8B 2026.03	72.1	-	-	-	-	-	75.7	-
TRUST-SQL-4B 2026.03	71.6	-	-	-	-	-	73.8	-
MTIR-SQL-4B 2026.03	71.2	-	-	-	-	-	-	-
Spider+BIRD+DataFlow-Text2SQL-90K 2025.12	71	-	-	-	-	-	73.1	-
DataFlow-Text2SQL-50K 2025.12	69.7	-	-	-	-	-	71.2	-
DataFlow-Text2SQL-90K 2025.12	69.7	-	-	-	-	-	71	-
Spider+BIRD+DataFlow-Text2SQL-90K 2025.12	67.7	-	-	-	-	-	69.7	-
Multi-turn Agent 2026.01	67.5	-	-	-	-	-	73.6	-
Qwen2.5-Coder-7B-Instruct 2025.12	67.5	-	-	-	-	-	73.6	-
SynSQL(50K) 2025.12	67.1	-	-	-	-	-	69.5	-
DataFlow-Text2SQL-90K 2025.12	66.5	-	-	-	-	-	67.7	-
DataFlow-Text2SQL-50K 2025.12	65.9	-	-	-	-	-	68.1	-
SynSQL(90K) 2025.12	65	-	-	-	-	-	70.7	-
SynSQL(50K) 2025.12	63.8	-	-	-	-	-	66.1	-
Qwen2.5-7B-Instruct 2025.12	63.7	-	-	-	-	-	71.8	-
OpenCoder-8B-Instruct 2025.12	62.6	-	-	-	-	-	64.7	-
Meta-Llama-3.1-8B-Instruct 2025.12	62.6	-	-	-	-	-	69.9	-
SynSQL(90K) 2025.12	61.8	-	-	-	-	-	67.4	-
DeepSeek-Coder-7B-Instruct 2025.12	60.9	-	-	-	-	-	64.1	-
Granite-3.1-8B-Instruct 2025.12	60	-	-	-	-	-	66.5	-
Granite-8B-Code-Instruct 2025.12	50.7	-	-	-	-	-	54.4	-
ACT-SQL 2025.05	-	72	47.7	-	-	-	-	-
ASTRES 2025.05	-	72.3	59.1	-	-	-	-	-
DCG-SQL 2025.05	-	71.6	66.5	-	-	-	-	-
DIN-SQL 2025.05	-	64.3	36.6	-	-	-	-	-
ACT-SQL 2025.05	-	68.2	45.4	-	-	-	-	-
ASTRES 2025.05	-	68.8	49.3	-	-	-	-	-
DCG-SQL 2025.05	-	69	59.4	-	-	-	-	-
ACT-SQL 2025.05	-	69.5	47.5	-	-	-	-	-
ASTRES 2025.05	-	70.5	46.4	-	-	-	-	-
DCG-SQL 2025.05	-	68.4	62.8	-	-	-	-	-
DIN-SQL 2025.05	-	56.3	44.1	-	-	-	-	-
ACT-SQL 2025.05	-	63.6	48	-	-	-	-	-
DCG-SQL 2025.05	-	66.5	60.2	-	-	-	-	-
DIN-SQL 2025.05	-	54.1	16.3	-	-	-	-	-
ACT-SQL 2025.05	-	63.2	44.9	-	-	-	-	-
DCG-SQL 2025.05	-	65	55.5	-	-	-	-	-
DIN-SQL 2025.05	-	35.7	27.5	-	-	-	-	-
ACT-SQL 2025.05	-	54.4	41.7	-	-	-	-	-
DCG-SQL 2025.05	-	59.1	52.5	-	-	-	-	-
o3-mini 2025.11	-	-	-	75.54	67.61	60.52	-	-
GPT-4.1 2025.11	-	-	-	76.28	72.19	62.12	-	-
DeepSeek-R1-250120 2025.11	-	-	-	77.2	77.41	64.55	-	-
Deepseek-V3-241226 2025.11	-	-	-	72.85	63.29	57.7	-	-
Kimi-K2 2025.11	-	-	-	75.79	67.5	60.7	-	-
DeepSeek-Coder-6.7B-Instruct 2025.11	-	-	-	58.75	53.54	44.67	-	-
Qwen2.5-Coder-7B-Instruct 2025.11	-	-	-	60.85	44.17	48.17	-	-
Qwen2.5-Coder-14B-Instruct 2025.11	-	-	-	66.04	52.96	51.77	-	-
Qwen2.5-Coder-7B-Instruct 2025.11	-	-	-	56.95	63.83	38.44	-	-
Qwen2.5-Coder-14B-Instruct 2025.11	-	-	-	70.15	75.49	56.19	-	-
RuCo-C 2025.11	-	-	-	75.6	77.84	63.12	-	-
RuCo-C 2025.11	-	-	-	70.08	77.41	56.29	-	-
SQL-R1 2026.01	-	-	-	-	-	-	78.1	-
Base Model 2026.01	-	67.5	-	-	-	-	-	53.4
SFT (BIRD+Spider) 2026.01	-	65.8	-	-	-	-	-	55.8
OmniSQL-7B 2026.01	-	76.1	-	-	-	-	-	61.4
EVOLSQL-7B 2026.01	-	74.2	-	-	-	-	-	61.9
Think2SQL-4B 2025.04	-	76	-	-	-	-	-	-
Think2SQL-8B 2025.04	-	75.9	-	-	-	-	-	-
Think2SQL-14B 2025.04	-	77.8	-	-	-	-	-	-
SQL-R1-3B 2026.03	-	-	-	-	-	-	70.5	-
SQL-R1-7B 2026.03	-	-	-	-	-	-	78.1	-