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
Vals SWE-bench Multimodal evaluation. Every model the catalog carries a published SWE-bench Multimodal (Vals) value for, ranked by that value.
JavaScript issue resolution where bug reports depend on screenshots, evaluated by Vals AI with no agent internet access.
The benchmark is defined by SWE-bench Multimodal on Vals AI, 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.
SWE-bench Multimodal (Vals) (Vals SWE-bench Multimodal evaluation) is an external benchmark published by SWE-bench Multimodal on Vals AI. JavaScript issue resolution where bug reports depend on screenshots, evaluated by Vals AI with no agent internet access. Its evaluation set is described by the source as 480 JavaScript issues with visual bug reports. The source rates its difficulty as visual software issue resolution.
Each model's result is published by SWE-bench Multimodal on Vals AI as resolved issue percentage. ModelScale prints that value to 2 decimal places, 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.