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.

91
cerebras/llama-4-maverick-17b-128e-instruct
Average duration
4s
Average tokens
941
Average cost
$0.00
100
4s
600
opper_sql_sample_01
100
3s
623
opper_sql_sample_02
100
3s
632
opper_sql_sample_03
100
3s
610
opper_sql_sample_04
100
3s
664
opper_sql_sample_05
100
3s
728
opper_sql_sample_06
100
3s
616
opper_sql_sample_07
100
3s
618
opper_sql_sample_08
100
3s
629
opper_sql_sample_09
100
3s
670
opper_sql_sample_10
100
3s
826
opper_sql_sample_11
75
3s
844
opper_sql_sample_12
100
3s
891
opper_sql_sample_13
100
3s
911
opper_sql_sample_14
75
3s
913
opper_sql_sample_15
100
3s
937
opper_sql_sample_16
100
3s
894
opper_sql_sample_17
75
3s
950
opper_sql_sample_18
50
3s
888
opper_sql_sample_19
75
3s
972
opper_sql_sample_20
100
3s
1035
opper_sql_sample_21
75
4s
1099
opper_sql_sample_22
100
3s
1143
opper_sql_sample_23
50
4s
1068
opper_sql_sample_24
100
4s
1123
opper_sql_sample_25
75
8s
1816
opper_sql_sample_26
100
5s
1400
opper_sql_sample_27
75
3s
1170
opper_sql_sample_28
100
5s
1694
opper_sql_sample_29
100
5s
1260
opper_sql_sample_30