swebenchpro

v1.0

SWE-bench Pro: A multi-language software engineering benchmark with 731 instances covering Python, JavaScript/TypeScript, and Go. Evaluates AI systems' ability to resolve real-world bugs and implement features across diverse production codebases. Original benchmark: https://github.com/scaleapi/SWE-bench_Pro-os. Adapter details: https://github.com/laude-institute/harbor/tree/main/adapters/swebenchpro

harbor run -d swebenchpro@1.0

Tasks (731)

instance_qutebrowser__qutebrowser-ed19d7f58b2664bb310c7cb6b52c5b9a06ea60b2-v059c6fdc75567943479b23ebca7c07b5e9a7f34c
harbor run -d swebenchpro@1.0 -t instance_qutebrowser__qutebrowser-ed19d7f58b2664bb310c7cb6b52c5b9a06ea60b2-v059c6fdc75567943479b23ebca7c07b5e9a7f34c
c3cf63b
instance_qutebrowser__qutebrowser-ef5ba1a0360b39f9eff027fbdc57f363597c3c3b-v363c8a7e5ccdf6968fc7ab84a2053ac78036691d
harbor run -d swebenchpro@1.0 -t instance_qutebrowser__qutebrowser-ef5ba1a0360b39f9eff027fbdc57f363597c3c3b-v363c8a7e5ccdf6968fc7ab84a2053ac78036691d
c3cf63b
instance_qutebrowser__qutebrowser-f631cd4422744160d9dcf7a0455da532ce973315-v35616345bb8052ea303186706cec663146f0f184
harbor run -d swebenchpro@1.0 -t instance_qutebrowser__qutebrowser-f631cd4422744160d9dcf7a0455da532ce973315-v35616345bb8052ea303186706cec663146f0f184
c3cf63b
instance_qutebrowser__qutebrowser-f7753550f2c1dcb2348e4779fd5287166754827e-v059c6fdc75567943479b23ebca7c07b5e9a7f34c
harbor run -d swebenchpro@1.0 -t instance_qutebrowser__qutebrowser-f7753550f2c1dcb2348e4779fd5287166754827e-v059c6fdc75567943479b23ebca7c07b5e9a7f34c
c3cf63b
instance_qutebrowser__qutebrowser-f8e7fea0becae25ae20606f1422068137189fe9e
harbor run -d swebenchpro@1.0 -t instance_qutebrowser__qutebrowser-f8e7fea0becae25ae20606f1422068137189fe9e
c3cf63b
instance_qutebrowser__qutebrowser-f91ace96223cac8161c16dd061907e138fe85111-v059c6fdc75567943479b23ebca7c07b5e9a7f34c
harbor run -d swebenchpro@1.0 -t instance_qutebrowser__qutebrowser-f91ace96223cac8161c16dd061907e138fe85111-v059c6fdc75567943479b23ebca7c07b5e9a7f34c
c3cf63b
instance_qutebrowser__qutebrowser-fcfa069a06ade76d91bac38127f3235c13d78eb1-v5fc38aaf22415ab0b70567368332beee7955b367
harbor run -d swebenchpro@1.0 -t instance_qutebrowser__qutebrowser-fcfa069a06ade76d91bac38127f3235c13d78eb1-v5fc38aaf22415ab0b70567368332beee7955b367
c3cf63b
instance_qutebrowser__qutebrowser-fd6790fe8c02b144ab2464f1fc8ab3d02ce3c476-v2ef375ac784985212b1805e1d0431dc8f1b3c171
harbor run -d swebenchpro@1.0 -t instance_qutebrowser__qutebrowser-fd6790fe8c02b144ab2464f1fc8ab3d02ce3c476-v2ef375ac784985212b1805e1d0431dc8f1b3c171
c3cf63b
instance_qutebrowser__qutebrowser-fea33d607fde83cf505b228238cf365936437a63-v9f8e9d96c85c85a605e382f1510bd08563afc566
harbor run -d swebenchpro@1.0 -t instance_qutebrowser__qutebrowser-fea33d607fde83cf505b228238cf365936437a63-v9f8e9d96c85c85a605e382f1510bd08563afc566
c3cf63b
instance_qutebrowser__qutebrowser-fec187c2cb53d769c2682b35ca77858a811414a8-v363c8a7e5ccdf6968fc7ab84a2053ac78036691d
harbor run -d swebenchpro@1.0 -t instance_qutebrowser__qutebrowser-fec187c2cb53d769c2682b35ca77858a811414a8-v363c8a7e5ccdf6968fc7ab84a2053ac78036691d
c3cf63b
instance_qutebrowser__qutebrowser-ff1c025ad3210506fc76e1f604d8c8c27637d88e-v363c8a7e5ccdf6968fc7ab84a2053ac78036691d
harbor run -d swebenchpro@1.0 -t instance_qutebrowser__qutebrowser-ff1c025ad3210506fc76e1f604d8c8c27637d88e-v363c8a7e5ccdf6968fc7ab84a2053ac78036691d
c3cf63b
instance_tutao__tutanota-09c2776c0fce3db5c6e18da92b5a45dce9f013aa-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-09c2776c0fce3db5c6e18da92b5a45dce9f013aa-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
c3cf63b
instance_tutao__tutanota-12a6cbaa4f8b43c2f85caca0787ab55501539955-vc4e41fd0029957297843cb9dec4a25c7c756f029
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-12a6cbaa4f8b43c2f85caca0787ab55501539955-vc4e41fd0029957297843cb9dec4a25c7c756f029
c3cf63b
instance_tutao__tutanota-1e516e989b3c0221f4af6b297d9c0e4c43e4adc3-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-1e516e989b3c0221f4af6b297d9c0e4c43e4adc3-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
c3cf63b
instance_tutao__tutanota-1ff82aa365763cee2d609c9d19360ad87fdf2ec7-vc4e41fd0029957297843cb9dec4a25c7c756f029
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-1ff82aa365763cee2d609c9d19360ad87fdf2ec7-vc4e41fd0029957297843cb9dec4a25c7c756f029
c3cf63b
instance_tutao__tutanota-219bc8f05d7b980e038bc1524cb021bf56397a1b-vee878bb72091875e912c52fc32bc60ec3760227b
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-219bc8f05d7b980e038bc1524cb021bf56397a1b-vee878bb72091875e912c52fc32bc60ec3760227b
c3cf63b
instance_tutao__tutanota-40e94dee2bcec2b63f362da283123e9df1874cc1-vc4e41fd0029957297843cb9dec4a25c7c756f029
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-40e94dee2bcec2b63f362da283123e9df1874cc1-vc4e41fd0029957297843cb9dec4a25c7c756f029
c3cf63b
instance_tutao__tutanota-4b4e45949096bb288f2b522f657610e480efa3e8-vee878bb72091875e912c52fc32bc60ec3760227b
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-4b4e45949096bb288f2b522f657610e480efa3e8-vee878bb72091875e912c52fc32bc60ec3760227b
c3cf63b
instance_tutao__tutanota-51818218c6ae33de00cbea3a4d30daac8c34142e-vc4e41fd0029957297843cb9dec4a25c7c756f029
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-51818218c6ae33de00cbea3a4d30daac8c34142e-vc4e41fd0029957297843cb9dec4a25c7c756f029
c3cf63b
instance_tutao__tutanota-8513a9e8114a8b42e64f4348335e0f23efa054c4-vee878bb72091875e912c52fc32bc60ec3760227b
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-8513a9e8114a8b42e64f4348335e0f23efa054c4-vee878bb72091875e912c52fc32bc60ec3760227b
c3cf63b
instance_tutao__tutanota-b4934a0f3c34d9d7649e944b183137e8fad3e859-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-b4934a0f3c34d9d7649e944b183137e8fad3e859-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
c3cf63b
instance_tutao__tutanota-befce4b146002b9abc86aa95f4d57581771815ce-vee878bb72091875e912c52fc32bc60ec3760227b
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-befce4b146002b9abc86aa95f4d57581771815ce-vee878bb72091875e912c52fc32bc60ec3760227b
c3cf63b
instance_tutao__tutanota-d1aa0ecec288bfc800cfb9133b087c4f81ad8b38-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-d1aa0ecec288bfc800cfb9133b087c4f81ad8b38-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
c3cf63b
instance_tutao__tutanota-da4edb7375c10f47f4ed3860a591c5e6557f7b5c-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-da4edb7375c10f47f4ed3860a591c5e6557f7b5c-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
c3cf63b
instance_tutao__tutanota-db90ac26ab78addf72a8efaff3c7acc0fbd6d000-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-db90ac26ab78addf72a8efaff3c7acc0fbd6d000-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
c3cf63b
instance_tutao__tutanota-de49d486feef842101506adf040a0f00ded59519-v10a26bfb45a064b93f4fc044a0254925037b88f1
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-de49d486feef842101506adf040a0f00ded59519-v10a26bfb45a064b93f4fc044a0254925037b88f1
c3cf63b
instance_tutao__tutanota-f373ac3808deefce8183dad8d16729839cc330c1-v2939aa9f4356f0dc9f523ee5ce19d09e08ab979b
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-f373ac3808deefce8183dad8d16729839cc330c1-v2939aa9f4356f0dc9f523ee5ce19d09e08ab979b
c3cf63b
instance_tutao__tutanota-f3ffe17af6e8ab007e8d461355057ad237846d9d-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-f3ffe17af6e8ab007e8d461355057ad237846d9d-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
c3cf63b
instance_tutao__tutanota-fb32e5f9d9fc152a00144d56dd0af01760a2d4dc-vc4e41fd0029957297843cb9dec4a25c7c756f029
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-fb32e5f9d9fc152a00144d56dd0af01760a2d4dc-vc4e41fd0029957297843cb9dec4a25c7c756f029
c3cf63b
instance_tutao__tutanota-fbdb72a2bd39b05131ff905780d9d4a2a074de26-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-fbdb72a2bd39b05131ff905780d9d4a2a074de26-vbc0d9ba8f0071fbe982809910959a6ff8884dbbf
c3cf63b
instance_tutao__tutanota-fe240cbf7f0fdd6744ef7bef8cb61676bcdbb621-vc4e41fd0029957297843cb9dec4a25c7c756f029
harbor run -d swebenchpro@1.0 -t instance_tutao__tutanota-fe240cbf7f0fdd6744ef7bef8cb61676bcdbb621-vc4e41fd0029957297843cb9dec4a25c7c756f029
c3cf63b