Benchmarks
Benchmarks
CursorBench
Codingunit % · normalized over [0, 80]CursorBench 3.2 — Cursor's independently-run agentic coding evaluation over real editor sessions. Reported by vendors from Cursor's runs rather than self-administered.
#ModelSourceScoreNormalized
Score distribution
6 tracked results across the normalization window
080
Score vs. parameters
Open-weights models, log-x params
No open-weights models with disclosed parameter counts have a score here yet.