Skip to content

CodyBench Results

Benchmarks updated weekly by GitHub Actions.

How It Works

CodyBench runs A/B comparisons: same task with CodyMaster vs without. Each suite runs 3 times per platform. Scores are 0–100.

Latest Results

SuiteWith CMWithout CMDeltaDate
TDD Regression Catch Ratepending
Token Efficiencypending
Memory Retentionpending

Run cm bench locally to generate results.

Research Basis

  • SkillsBench (peer-reviewed): curated skills +16.2pp, 2-3 focused skills +18.6pp
  • Goose benchmark methodology: transparent runs, 3× repeat, publish even early/small results

CodyMaster — AI-assisted engineering toolkit