bird-bench

vparity

BIRD SQL parity subset (150 tasks, seed 42). Original benchmark: https://huggingface.co/datasets/birdsql/bird_sql_dev_20251106. Adapter: https://github.com/laude-institute/harbor/tree/main/adapters/bird-bench.

uvx harbor run -d bird-bench@parity

Tasks (150)

california_schools__13
uvx harbor run -d bird-bench@parity -t california_schools__13
b05ea1d
california_schools__23
uvx harbor run -d bird-bench@parity -t california_schools__23
b05ea1d
california_schools__3
uvx harbor run -d bird-bench@parity -t california_schools__3
b05ea1d
california_schools__37
uvx harbor run -d bird-bench@parity -t california_schools__37
b05ea1d
california_schools__43
uvx harbor run -d bird-bench@parity -t california_schools__43
b05ea1d
california_schools__65
uvx harbor run -d bird-bench@parity -t california_schools__65
b05ea1d
california_schools__74
uvx harbor run -d bird-bench@parity -t california_schools__74
b05ea1d
california_schools__75
uvx harbor run -d bird-bench@parity -t california_schools__75
b05ea1d
california_schools__87
uvx harbor run -d bird-bench@parity -t california_schools__87
b05ea1d
card_games__350
uvx harbor run -d bird-bench@parity -t card_games__350
b05ea1d
card_games__362
uvx harbor run -d bird-bench@parity -t card_games__362
b05ea1d
card_games__402
uvx harbor run -d bird-bench@parity -t card_games__402
b05ea1d
card_games__410
uvx harbor run -d bird-bench@parity -t card_games__410
b05ea1d
card_games__412
uvx harbor run -d bird-bench@parity -t card_games__412
b05ea1d
card_games__438
uvx harbor run -d bird-bench@parity -t card_games__438
b05ea1d
card_games__444
uvx harbor run -d bird-bench@parity -t card_games__444
b05ea1d
card_games__445
uvx harbor run -d bird-bench@parity -t card_games__445
b05ea1d
card_games__450
uvx harbor run -d bird-bench@parity -t card_games__450
b05ea1d
card_games__451
uvx harbor run -d bird-bench@parity -t card_games__451
b05ea1d
card_games__454
uvx harbor run -d bird-bench@parity -t card_games__454
b05ea1d
card_games__458
uvx harbor run -d bird-bench@parity -t card_games__458
b05ea1d
card_games__469
uvx harbor run -d bird-bench@parity -t card_games__469
b05ea1d
card_games__474
uvx harbor run -d bird-bench@parity -t card_games__474
b05ea1d
card_games__487
uvx harbor run -d bird-bench@parity -t card_games__487
b05ea1d
codebase_community__542
uvx harbor run -d bird-bench@parity -t codebase_community__542
b05ea1d
codebase_community__545
uvx harbor run -d bird-bench@parity -t codebase_community__545
b05ea1d
codebase_community__570
uvx harbor run -d bird-bench@parity -t codebase_community__570
b05ea1d
codebase_community__575
uvx harbor run -d bird-bench@parity -t codebase_community__575
b05ea1d
codebase_community__579
uvx harbor run -d bird-bench@parity -t codebase_community__579
b05ea1d
codebase_community__599
uvx harbor run -d bird-bench@parity -t codebase_community__599
b05ea1d
codebase_community__602
uvx harbor run -d bird-bench@parity -t codebase_community__602
b05ea1d
codebase_community__620
uvx harbor run -d bird-bench@parity -t codebase_community__620
b05ea1d
codebase_community__634
uvx harbor run -d bird-bench@parity -t codebase_community__634
b05ea1d
codebase_community__639
uvx harbor run -d bird-bench@parity -t codebase_community__639
b05ea1d
codebase_community__643
uvx harbor run -d bird-bench@parity -t codebase_community__643
b05ea1d
codebase_community__678
uvx harbor run -d bird-bench@parity -t codebase_community__678
b05ea1d
codebase_community__681
uvx harbor run -d bird-bench@parity -t codebase_community__681
b05ea1d
codebase_community__688
uvx harbor run -d bird-bench@parity -t codebase_community__688
b05ea1d
codebase_community__697
uvx harbor run -d bird-bench@parity -t codebase_community__697
b05ea1d
codebase_community__712
uvx harbor run -d bird-bench@parity -t codebase_community__712
b05ea1d
codebase_community__715
uvx harbor run -d bird-bench@parity -t codebase_community__715
b05ea1d
debit_card_specializing__1478
uvx harbor run -d bird-bench@parity -t debit_card_specializing__1478
b05ea1d
debit_card_specializing__1485
uvx harbor run -d bird-bench@parity -t debit_card_specializing__1485
b05ea1d
debit_card_specializing__1488
uvx harbor run -d bird-bench@parity -t debit_card_specializing__1488
b05ea1d
debit_card_specializing__1493
uvx harbor run -d bird-bench@parity -t debit_card_specializing__1493
b05ea1d
debit_card_specializing__1501
uvx harbor run -d bird-bench@parity -t debit_card_specializing__1501
b05ea1d
debit_card_specializing__1502
uvx harbor run -d bird-bench@parity -t debit_card_specializing__1502
b05ea1d
debit_card_specializing__1532
uvx harbor run -d bird-bench@parity -t debit_card_specializing__1532
b05ea1d
european_football_2__1026
uvx harbor run -d bird-bench@parity -t european_football_2__1026
b05ea1d
european_football_2__1030
uvx harbor run -d bird-bench@parity -t european_football_2__1030
b05ea1d
european_football_2__1041
uvx harbor run -d bird-bench@parity -t european_football_2__1041
b05ea1d
european_football_2__1050
uvx harbor run -d bird-bench@parity -t european_football_2__1050
b05ea1d
european_football_2__1058
uvx harbor run -d bird-bench@parity -t european_football_2__1058
b05ea1d
european_football_2__1062
uvx harbor run -d bird-bench@parity -t european_football_2__1062
b05ea1d
european_football_2__1066
uvx harbor run -d bird-bench@parity -t european_football_2__1066
b05ea1d
european_football_2__1084
uvx harbor run -d bird-bench@parity -t european_football_2__1084
b05ea1d
european_football_2__1090
uvx harbor run -d bird-bench@parity -t european_football_2__1090
b05ea1d
european_football_2__1093
uvx harbor run -d bird-bench@parity -t european_football_2__1093
b05ea1d
european_football_2__1112
uvx harbor run -d bird-bench@parity -t european_football_2__1112
b05ea1d
european_football_2__1116
uvx harbor run -d bird-bench@parity -t european_football_2__1116
b05ea1d
european_football_2__1133
uvx harbor run -d bird-bench@parity -t european_football_2__1133
b05ea1d
european_football_2__1141
uvx harbor run -d bird-bench@parity -t european_football_2__1141
b05ea1d
financial__110
uvx harbor run -d bird-bench@parity -t financial__110
b05ea1d
financial__117
uvx harbor run -d bird-bench@parity -t financial__117
b05ea1d
financial__118
uvx harbor run -d bird-bench@parity -t financial__118
b05ea1d
financial__132
uvx harbor run -d bird-bench@parity -t financial__132
b05ea1d
financial__158
uvx harbor run -d bird-bench@parity -t financial__158
b05ea1d
financial__181
uvx harbor run -d bird-bench@parity -t financial__181
b05ea1d
financial__193
uvx harbor run -d bird-bench@parity -t financial__193
b05ea1d
financial__89
uvx harbor run -d bird-bench@parity -t financial__89
b05ea1d
financial__90
uvx harbor run -d bird-bench@parity -t financial__90
b05ea1d
formula_1__1007
uvx harbor run -d bird-bench@parity -t formula_1__1007
b05ea1d
formula_1__848
uvx harbor run -d bird-bench@parity -t formula_1__848
b05ea1d
formula_1__876
uvx harbor run -d bird-bench@parity -t formula_1__876
b05ea1d
formula_1__891
uvx harbor run -d bird-bench@parity -t formula_1__891
b05ea1d
formula_1__900
uvx harbor run -d bird-bench@parity -t formula_1__900
b05ea1d
formula_1__902
uvx harbor run -d bird-bench@parity -t formula_1__902
b05ea1d
formula_1__905
uvx harbor run -d bird-bench@parity -t formula_1__905
b05ea1d
formula_1__912
uvx harbor run -d bird-bench@parity -t formula_1__912
b05ea1d
formula_1__924
uvx harbor run -d bird-bench@parity -t formula_1__924
b05ea1d
formula_1__931
uvx harbor run -d bird-bench@parity -t formula_1__931
b05ea1d
formula_1__936
uvx harbor run -d bird-bench@parity -t formula_1__936
b05ea1d
formula_1__938
uvx harbor run -d bird-bench@parity -t formula_1__938
b05ea1d
formula_1__965
uvx harbor run -d bird-bench@parity -t formula_1__965
b05ea1d
formula_1__972
uvx harbor run -d bird-bench@parity -t formula_1__972
b05ea1d
formula_1__975
uvx harbor run -d bird-bench@parity -t formula_1__975
b05ea1d
formula_1__976
uvx harbor run -d bird-bench@parity -t formula_1__976
b05ea1d
formula_1__989
uvx harbor run -d bird-bench@parity -t formula_1__989
b05ea1d
student_club__1329
uvx harbor run -d bird-bench@parity -t student_club__1329
b05ea1d
student_club__1330
uvx harbor run -d bird-bench@parity -t student_club__1330
b05ea1d
student_club__1336
uvx harbor run -d bird-bench@parity -t student_club__1336
b05ea1d
student_club__1342
uvx harbor run -d bird-bench@parity -t student_club__1342
b05ea1d
student_club__1350
uvx harbor run -d bird-bench@parity -t student_club__1350
b05ea1d
student_club__1357
uvx harbor run -d bird-bench@parity -t student_club__1357
b05ea1d
student_club__1367
uvx harbor run -d bird-bench@parity -t student_club__1367
b05ea1d
student_club__1368
uvx harbor run -d bird-bench@parity -t student_club__1368
b05ea1d
student_club__1385
uvx harbor run -d bird-bench@parity -t student_club__1385
b05ea1d
student_club__1405
uvx harbor run -d bird-bench@parity -t student_club__1405
b05ea1d
student_club__1418
uvx harbor run -d bird-bench@parity -t student_club__1418
b05ea1d
student_club__1419
uvx harbor run -d bird-bench@parity -t student_club__1419
b05ea1d