Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
external benchmark
SWT-bench Verified: writing tests that reproduce real GitHub issues. Every model the catalog carries a published SWT-bench Verified value for, ranked by that value.
A test generation benchmark from LogicStar AI and ETH Zurich's SRI Lab. For each of 433 real GitHub issues from SWE-bench Verified, an agent writes a test that reproduces the reported bug: the test has to fail on the original code and pass once the issue's fix is applied. The score is the share of issues reproduced this way. 0 models in the ModelScale catalog have a published value.
The benchmark is defined by SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
What the benchmark measures and how its value is published, from the source’s own record.
SWT-bench Verified (SWT-bench Verified: writing tests that reproduce real GitHub issues) is an external benchmark published by SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents. A test generation benchmark from LogicStar AI and ETH Zurich's SRI Lab. For each of 433 real GitHub issues from SWE-bench Verified, an agent writes a test that reproduces the reported bug: the test has to fail on the original code and pass once the issue's fix is applied. The score is the share of issues reproduced this way. Its evaluation set is described by the source as 433 human-verified GitHub issues from SWE-bench Verified (Python repositories); SWT-bench Lite has 276 issues from SWE-bench Lite. The source rates its difficulty as reproducing a bug from an issue report as a failing test inside a real project's test suite.
Each model's result is published by SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents as agent or model gets the issue and the pre-fix repository and adds tests; tests run before and after the reference fix. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.