SQL

Natural language to SQL query generation evaluates text-to-query fidelity and schema reasoning. This task is particularly relevant for analytics chat assistants and simplified database interfaces where users need to query data using natural language. Models must understand both the intent behind the question and the structure of the underlying database schema.

94
anthropic/claude-3.7-sonnet
Average duration
7s
Average tokens
1106
Average cost
$0.00
100
6s
755
opper_sql_sample_01
100
9s
783
opper_sql_sample_02
100
9s
758
opper_sql_sample_03
100
6s
764
opper_sql_sample_04
100
5s
813
opper_sql_sample_05
100
7s
875
opper_sql_sample_06
100
7s
758
opper_sql_sample_07
75
7s
766
opper_sql_sample_08
100
5s
762
opper_sql_sample_09
100
6s
832
opper_sql_sample_10
100
8s
1038
opper_sql_sample_11
100
5s
1062
opper_sql_sample_12
100
8s
1108
opper_sql_sample_13
100
5s
1113
opper_sql_sample_14
75
7s
1137
opper_sql_sample_15
100
7s
1206
opper_sql_sample_16
100
7s
1141
opper_sql_sample_17
100
8s
1267
opper_sql_sample_18
50
6s
1125
opper_sql_sample_19
100
7s
1202
opper_sql_sample_20
100
5s
1278
opper_sql_sample_21
100
7s
1382
opper_sql_sample_22
100
8s
1439
opper_sql_sample_23
75
7s
1412
opper_sql_sample_24
75
7s
1444
opper_sql_sample_25
100
6s
1420
opper_sql_sample_26
100
7s
1346
opper_sql_sample_27
75
6s
1446
opper_sql_sample_28
100
8s
1448
opper_sql_sample_29
100
6s
1294
opper_sql_sample_30