{"id":"swe-bench-pro","name":"SWE-Bench Pro","maker":"Scale AI","url":"https://scale.com/leaderboard/swe_bench_pro_public","repo":"scaleapi/SWE-bench_Pro-os","summary":"A software engineering benchmark of longer-horizon tasks, with a public leaderboard from Scale AI.","details":"Contains tasks that need larger changes across several files in public and commercial-style repositories, scored by running tests. The public set and evaluation code are in the repository under the MIT licence, and Scale AI hosts the leaderboard.","open_source":true,"hosted":true,"verified":"2026-11-15","category":"benchmarks","category_name":"Agent benchmarks","page":"https://modelmoot.com/tools/swe-bench-pro","reviewed":"2026-11-15","checked":{"at":"2026-11-15T16:10:15.342Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}