Question 1

What is CursorBench?

Accepted Answer

Cursor's agentic-coding benchmark built from real, anonymized Cursor sessions: ambiguous, multi-file tasks spanning codebase understanding, bug finding, planning, code review, editing, refactoring, and bug fixes. Each model is evaluated across reasoning-effort levels; alongside the headline pass score, Cursor reports average cost per task (USD), tokens per task, and steps per task. Cursor cautions that small score differences may not be statistically meaningful. It is a agents benchmark measured by score.

Question 2

What does score mean on CursorBench?

Accepted Answer

CursorBench reports score (%); higher is better. Scores are shown only within CursorBench and are never averaged with other benchmarks.

Question 3

What is the top reported CursorBench score?

Accepted Answer

Claude Fable 5 has the top reported score on CursorBench: 72.9% (score).

Question 4

Why do CursorBench scores differ across runs?

Accepted Answer

Harness, scaffold, reasoning effort, and prompt setup change results, so two runs of the same model can differ. evals.report keeps each score with its run context so the differences stay visible.

Question 5

Does evals.report rank models across benchmarks?

Accepted Answer

No. CursorBench scores are shown within their own metric; evals.report never combines benchmarks into a composite ranking or a single "best model".