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.

71
mistral/mistral-small-eu
Average duration
9s
Average tokens
1089
Average cost
$0.00
100
3s
700
opper_sql_sample_01
100
4s
732
opper_sql_sample_02
100
4s
730
opper_sql_sample_03
100
10s
718
opper_sql_sample_04
100
12s
760
opper_sql_sample_05
100
29s
818
opper_sql_sample_06
100
5s
700
opper_sql_sample_07
100
4s
719
opper_sql_sample_08
100
3s
708
opper_sql_sample_09
100
4s
767
opper_sql_sample_10
100
4s
1005
opper_sql_sample_11
75
4s
1049
opper_sql_sample_12
25
31s
1061
opper_sql_sample_13
0
6s
1153
opper_sql_sample_14
50
6s
1112
opper_sql_sample_15
50
21s
1538
opper_sql_sample_16
100
5s
1111
opper_sql_sample_17
0
40s
1215
opper_sql_sample_18
0
6s
1091
opper_sql_sample_19
100
6s
1197
opper_sql_sample_20
100
4s
1240
opper_sql_sample_21
75
6s
1356
opper_sql_sample_22
25
6s
1357
opper_sql_sample_23
50
7s
1369
opper_sql_sample_24
50
6s
1400
opper_sql_sample_25
100
5s
1348
opper_sql_sample_26
50
10s
1304
opper_sql_sample_27
75
8s
1478
opper_sql_sample_28
0
9s
1323
opper_sql_sample_29
100
6s
1614
opper_sql_sample_30