swtbench-verified
v1.0SWTBench Verified - Software Testing Benchmark for code generation
uvx harbor run -d swtbench-verified@1.0Tasks (433)
pytest-dev__pytest-5840
uvx harbor run -d swtbench-verified@1.0 -t pytest-dev__pytest-5840e39578f
pytest-dev__pytest-6197
uvx harbor run -d swtbench-verified@1.0 -t pytest-dev__pytest-6197e39578f
pytest-dev__pytest-6202
uvx harbor run -d swtbench-verified@1.0 -t pytest-dev__pytest-6202e39578f
pytest-dev__pytest-7236
uvx harbor run -d swtbench-verified@1.0 -t pytest-dev__pytest-7236e39578f
pytest-dev__pytest-7324
uvx harbor run -d swtbench-verified@1.0 -t pytest-dev__pytest-7324e39578f
pytest-dev__pytest-7432
uvx harbor run -d swtbench-verified@1.0 -t pytest-dev__pytest-7432e39578f
pytest-dev__pytest-7521
uvx harbor run -d swtbench-verified@1.0 -t pytest-dev__pytest-7521e39578f
pytest-dev__pytest-7982
uvx harbor run -d swtbench-verified@1.0 -t pytest-dev__pytest-7982e39578f
scikit-learn__scikit-learn-10297
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-10297e39578f
scikit-learn__scikit-learn-10844
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-10844e39578f
scikit-learn__scikit-learn-10908
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-10908e39578f
scikit-learn__scikit-learn-11310
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-11310e39578f
scikit-learn__scikit-learn-11578
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-11578e39578f
scikit-learn__scikit-learn-12585
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-12585e39578f
scikit-learn__scikit-learn-12682
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-12682e39578f
scikit-learn__scikit-learn-12973
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-12973e39578f
scikit-learn__scikit-learn-13124
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-13124e39578f
scikit-learn__scikit-learn-13135
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-13135e39578f
scikit-learn__scikit-learn-13142
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-13142e39578f
scikit-learn__scikit-learn-13328
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-13328e39578f
scikit-learn__scikit-learn-13439
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-13439e39578f
scikit-learn__scikit-learn-13496
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-13496e39578f
scikit-learn__scikit-learn-13779
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-13779e39578f
scikit-learn__scikit-learn-14053
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-14053e39578f
scikit-learn__scikit-learn-14087
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-14087e39578f
scikit-learn__scikit-learn-14141
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-14141e39578f
scikit-learn__scikit-learn-14496
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-14496e39578f
scikit-learn__scikit-learn-14629
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-14629e39578f
scikit-learn__scikit-learn-14894
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-14894e39578f
scikit-learn__scikit-learn-14983
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-14983e39578f
scikit-learn__scikit-learn-15100
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-15100e39578f
scikit-learn__scikit-learn-9288
uvx harbor run -d swtbench-verified@1.0 -t scikit-learn__scikit-learn-9288e39578f
sphinx-doc__sphinx-10449
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-10449e39578f
sphinx-doc__sphinx-10466
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-10466e39578f
sphinx-doc__sphinx-10614
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-10614e39578f
sphinx-doc__sphinx-10673
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-10673e39578f
sphinx-doc__sphinx-11445
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-11445e39578f
sphinx-doc__sphinx-11510
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-11510e39578f
sphinx-doc__sphinx-8459
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-8459e39578f
sphinx-doc__sphinx-8475
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-8475e39578f
sphinx-doc__sphinx-8548
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-8548e39578f
sphinx-doc__sphinx-8551
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-8551e39578f
sphinx-doc__sphinx-8593
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-8593e39578f
sphinx-doc__sphinx-8595
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-8595e39578f
sphinx-doc__sphinx-8621
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-8621e39578f
sphinx-doc__sphinx-8638
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-8638e39578f
sphinx-doc__sphinx-8721
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-8721e39578f
sphinx-doc__sphinx-9229
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9229e39578f
sphinx-doc__sphinx-9230
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9230e39578f
sphinx-doc__sphinx-9258
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9258e39578f
sphinx-doc__sphinx-9281
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9281e39578f
sphinx-doc__sphinx-9320
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9320e39578f
sphinx-doc__sphinx-9367
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9367e39578f
sphinx-doc__sphinx-9461
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9461e39578f
sphinx-doc__sphinx-9591
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9591e39578f
sphinx-doc__sphinx-9602
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9602e39578f
sphinx-doc__sphinx-9658
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9658e39578f
sphinx-doc__sphinx-9673
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9673e39578f
sphinx-doc__sphinx-9698
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9698e39578f
sphinx-doc__sphinx-9711
uvx harbor run -d swtbench-verified@1.0 -t sphinx-doc__sphinx-9711e39578f
sympy__sympy-11618
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-11618e39578f
sympy__sympy-12096
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-12096e39578f
sympy__sympy-12419
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-12419e39578f
sympy__sympy-12481
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-12481e39578f
sympy__sympy-12489
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-12489e39578f
sympy__sympy-13031
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-13031e39578f
sympy__sympy-13372
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-13372e39578f
sympy__sympy-13480
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-13480e39578f
sympy__sympy-13551
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-13551e39578f
sympy__sympy-13615
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-13615e39578f
sympy__sympy-13647
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-13647e39578f
sympy__sympy-13757
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-13757e39578f
sympy__sympy-13798
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-13798e39578f
sympy__sympy-13852
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-13852e39578f
sympy__sympy-13877
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-13877e39578f
sympy__sympy-13974
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-13974e39578f
sympy__sympy-14248
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-14248e39578f
sympy__sympy-14531
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-14531e39578f
sympy__sympy-14711
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-14711e39578f
sympy__sympy-14976
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-14976e39578f
sympy__sympy-15017
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-15017e39578f
sympy__sympy-15345
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-15345e39578f
sympy__sympy-15349
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-15349e39578f
sympy__sympy-15599
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-15599e39578f
sympy__sympy-15809
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-15809e39578f
sympy__sympy-15875
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-15875e39578f
sympy__sympy-15976
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-15976e39578f
sympy__sympy-16450
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-16450e39578f
sympy__sympy-16597
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-16597e39578f
sympy__sympy-16766
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-16766e39578f
sympy__sympy-16792
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-16792e39578f
sympy__sympy-16886
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-16886e39578f
sympy__sympy-17139
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-17139e39578f
sympy__sympy-17318
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-17318e39578f
sympy__sympy-17630
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-17630e39578f
sympy__sympy-17655
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-17655e39578f
sympy__sympy-18189
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-18189e39578f
sympy__sympy-18199
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-18199e39578f
sympy__sympy-18211
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-18211e39578f
sympy__sympy-18698
uvx harbor run -d swtbench-verified@1.0 -t sympy__sympy-18698e39578f