IDE-generated unit tests run but do not test.

VibeCheck evaluated Kiro, Antigravity and Cursor (all on Claude Sonnet 4.5) generating repository-grounded tests across 15 Python and JS/TS repositories, scored on runnability, assertion strength, logic and edge-case coverage, isolation and maintainability. Tests are usually runnable and frequently lack strong assertions and meaningful behavioral coverage; weak assertions and missing edge cases occur more often than blocking failures. arXiv 2609.05978 Gate on green-and-covered and you're measuring the dimension that already works.