bird-bench
vparityBIRD 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@parityTasks (150)
student_club__1423
uvx harbor run -d bird-bench@parity -t student_club__142382d1fb0
student_club__1428
uvx harbor run -d bird-bench@parity -t student_club__142882d1fb0
student_club__1438
uvx harbor run -d bird-bench@parity -t student_club__143882d1fb0
student_club__1445
uvx harbor run -d bird-bench@parity -t student_club__144582d1fb0
student_club__1449
uvx harbor run -d bird-bench@parity -t student_club__144982d1fb0
student_club__1456
uvx harbor run -d bird-bench@parity -t student_club__145682d1fb0
student_club__1457
uvx harbor run -d bird-bench@parity -t student_club__145782d1fb0
superhero__738
uvx harbor run -d bird-bench@parity -t superhero__73882d1fb0
superhero__746
uvx harbor run -d bird-bench@parity -t superhero__74682d1fb0
superhero__752
uvx harbor run -d bird-bench@parity -t superhero__75282d1fb0
superhero__764
uvx harbor run -d bird-bench@parity -t superhero__76482d1fb0
superhero__765
uvx harbor run -d bird-bench@parity -t superhero__76582d1fb0
superhero__786
uvx harbor run -d bird-bench@parity -t superhero__78682d1fb0
superhero__799
uvx harbor run -d bird-bench@parity -t superhero__79982d1fb0
superhero__802
uvx harbor run -d bird-bench@parity -t superhero__80282d1fb0
superhero__813
uvx harbor run -d bird-bench@parity -t superhero__81382d1fb0
superhero__814
uvx harbor run -d bird-bench@parity -t superhero__81482d1fb0
superhero__816
uvx harbor run -d bird-bench@parity -t superhero__81682d1fb0
thrombosis_prediction__1157
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__115782d1fb0
thrombosis_prediction__1162
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__116282d1fb0
thrombosis_prediction__1164
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__116482d1fb0
thrombosis_prediction__1168
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__116882d1fb0
thrombosis_prediction__1171
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__117182d1fb0
thrombosis_prediction__1192
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__119282d1fb0
thrombosis_prediction__1195
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__119582d1fb0
thrombosis_prediction__1202
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__120282d1fb0
thrombosis_prediction__1209
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__120982d1fb0
thrombosis_prediction__1222
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__122282d1fb0
thrombosis_prediction__1232
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__123282d1fb0
thrombosis_prediction__1248
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__124882d1fb0
thrombosis_prediction__1250
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__125082d1fb0
thrombosis_prediction__1254
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__125482d1fb0
thrombosis_prediction__1263
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__126382d1fb0
thrombosis_prediction__1269
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__126982d1fb0
thrombosis_prediction__1272
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__127282d1fb0
thrombosis_prediction__1302
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__130282d1fb0
thrombosis_prediction__1305
uvx harbor run -d bird-bench@parity -t thrombosis_prediction__130582d1fb0
toxicology__211
uvx harbor run -d bird-bench@parity -t toxicology__21182d1fb0
toxicology__223
uvx harbor run -d bird-bench@parity -t toxicology__22382d1fb0
toxicology__228
uvx harbor run -d bird-bench@parity -t toxicology__22882d1fb0
toxicology__229
uvx harbor run -d bird-bench@parity -t toxicology__22982d1fb0
toxicology__230
uvx harbor run -d bird-bench@parity -t toxicology__23082d1fb0
toxicology__269
uvx harbor run -d bird-bench@parity -t toxicology__26982d1fb0
toxicology__272
uvx harbor run -d bird-bench@parity -t toxicology__27282d1fb0
toxicology__293
uvx harbor run -d bird-bench@parity -t toxicology__29382d1fb0
toxicology__299
uvx harbor run -d bird-bench@parity -t toxicology__29982d1fb0
toxicology__307
uvx harbor run -d bird-bench@parity -t toxicology__30782d1fb0
toxicology__311
uvx harbor run -d bird-bench@parity -t toxicology__31182d1fb0
toxicology__313
uvx harbor run -d bird-bench@parity -t toxicology__31382d1fb0
toxicology__316
uvx harbor run -d bird-bench@parity -t toxicology__31682d1fb0