Categoryexternal
MeasurePass@1
Tasks50 Mercor tasks; 500 tasks in the separately reported original set
DifficultySource-specific evaluation
Editing repositories to resolve verified GitHub issues. This table shows Mercor-run configurations for reference and is excluded from model rankings.
No model in the catalog has a published SWE-bench Verified Extended (Mercor) score.The benchmark is defined by SWE-bench Verified Extended evaluation results, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
About SWE-bench Verified Extended (Mercor)
What the benchmark measures and how its value is published, from the source’s own record.
What is SWE-bench Verified Extended (Mercor)?
SWE-bench Verified Extended (Mercor) (SWE-bench Verified Extended — Mercor evaluation) is an external benchmark published by SWE-bench Verified Extended evaluation results. Editing repositories to resolve verified GitHub issues. This table shows Mercor-run configurations for reference and is excluded from model rankings. Its evaluation set is described by the source as 50 Mercor tasks; 500 tasks in the separately reported original set. The source rates its difficulty as source-specific evaluation.
How is SWE-bench Verified Extended (Mercor) scored?
Each model's result is published by SWE-bench Verified Extended evaluation results as pass@1. 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.
ModelScale