CoVer lifts code-generation pass@1 by up to 7.1 points
CoVer gives 7B and 14B code models a stronger way to generate and judge tests, raising one-shot pass@1 by 5.8 and 7.1 points across five benchmarks. It rewards tests whose pass/fail results track a ground-truth correctness signal, then removes behaviorally redundant tests to make each execution count more. Used in the CodeT ranking pipeline, CoVer-7B adds another 3.5 points.