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 Code Migration v1.1. Every model the catalog carries a published Code Migration v1.1 value for, ranked by that value.
Reimplementing working programs in another language using the Pi agent harness and revised hidden tests.
The benchmark is defined by Code Migration v1.1, 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.
Code Migration v1.1 (Vals Code Migration v1.1) is an external benchmark published by Code Migration v1.1. Reimplementing working programs in another language using the Pi agent harness and revised hidden tests. Its evaluation set is described by the source as 120 CLI migration tasks and 10 COBOL tasks. The source rates its difficulty as production code migration.
Each model's result is published by Code Migration v1.1 as 75% CLI and 25% COBOL accuracy. 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.