Coding benchmarks
Explore code generation, debugging, and software engineering evaluations, from focused programming tasks to changes in real repositories. Check the language, test environment, and tools available to each model.
Published
No benchmarks match this search
Try another benchmark name, capability or category.
Methodology and provenance
Benchize collects and structures public benchmark reports. Scores, costs, timings, ranks and uncertainty remain attributed to their original sources. Different versions, configurations and measurement units are separate results. Missing fields stay unavailable.