swebench-bash-only: by examples

Results Paper Code


Not solved by any model

There are 63 examples not solved by any model. Solving some of these can be a good signal that your model is indeed better than leading models if these are good problems.
astropy__astropy-13033, astropy__astropy-13398, astropy__astropy-13977, astropy__astropy-14598, astropy__astropy-7606, astropy__astropy-8707, astropy__astropy-8872, django__django-10554, django__django-10999, django__django-11087, django__django-11400, django__django-11820, django__django-13212, django__django-13513, django__django-13794, django__django-14011, django__django-14034, django__django-14155, django__django-14170, django__django-14315, django__django-14792, django__django-15098, django__django-15252, django__django-15629, django__django-15695, django__django-16256, django__django-16263, django__django-16502, django__django-16631, django__django-16667, matplotlib__matplotlib-23476, matplotlib__matplotlib-24870, matplotlib__matplotlib-25479, matplotlib__matplotlib-26208, matplotlib__matplotlib-26466, pydata__xarray-6992, pydata__xarray-7229, pylint-dev__pylint-4551, pylint-dev__pylint-4604, pylint-dev__pylint-4661, pylint-dev__pylint-6528, pylint-dev__pylint-7277, pytest-dev__pytest-10356, pytest-dev__pytest-5840, scikit-learn__scikit-learn-25747, scikit-learn__scikit-learn-26194, sphinx-doc__sphinx-10614, sphinx-doc__sphinx-11510, sphinx-doc__sphinx-7462, sphinx-doc__sphinx-7590, sphinx-doc__sphinx-7748, sphinx-doc__sphinx-7985, sphinx-doc__sphinx-9229, sphinx-doc__sphinx-9602, sympy__sympy-13852, sympy__sympy-16597, sympy__sympy-17630, sympy__sympy-18199, sympy__sympy-20428, sympy__sympy-20438, sympy__sympy-21596, sympy__sympy-21930, sympy__sympy-22080

Problems solved by 1 model only

example_link model min_pass1_of_model
django__django-12406 Claude 4.5 Opus medium (20251101) 0.744
sphinx-doc__sphinx-8548 Claude 4.5 Opus medium (20251101) 0.744
matplotlib__matplotlib-21568 Claude 4.5 Opus medium (20251101) 0.744
django__django-15957 Claude 4.5 Opus medium (20251101) 0.744
psf__requests-6028 Claude 4.5 Opus medium (20251101) 0.744
sphinx-doc__sphinx-9461 Claude 4.5 Opus medium (20251101) 0.744
django__django-11734 Gemini 3 Pro Preview (2025-11-18) 0.742
django__django-13344 Gemini 3 Pro Preview (2025-11-18) 0.742
django__django-11265 Gemini 3 Pro Preview (2025-11-18) 0.742
sympy__sympy-14248 Gemini 3 Pro Preview (2025-11-18) 0.742
sympy__sympy-13798 Claude 4.5 Sonnet (20250929) 0.706
django__django-13195 GPT-5.2 (2025-12-11) 0.690
django__django-11141 Minimax M2 0.610
pylint-dev__pylint-8898 Minimax M2 0.610
django__django-12273 GLM-4.6 (T=1) 0.554
psf__requests-1921 Qwen3-Coder 480B/A35B Instruct 0.554
matplotlib__matplotlib-23299 gpt-oss-120b 0.260

Suspect problems

These are 10 problems with the lowest correlation with the overall evaluation (i.e. better models tend to do worse on these. )

example_link pass1_of_ex tau
pytest-dev__pytest-7205 0.571 -0.324
psf__requests-2317 0.250 -0.268
sympy__sympy-18763 0.071 -0.236
psf__requests-1724 0.214 -0.229
matplotlib__matplotlib-23299 0.036 -0.208
psf__requests-1766 0.250 -0.136
sympy__sympy-23950 0.393 -0.109
psf__requests-1921 0.036 -0.060
django__django-12273 0.036 -0.060
django__django-11477 0.107 -0.042

Histogram of accuracies

Histogram of problems by the accuracy on each problem.

Histogram of difficulties

Histogram of problems by the minimum win rate to solve each problem.