Benchmark Radar™
Star —

CursorBench v3.2

Explore score history ↗

CursorBench v3.2 evaluates coding agents on interactive software engineering tasks in the Cursor environment.

Modality
text
Evaluates
agents, code
Openness
unknown
Importer
LLM Stats

Source provenance

CursorBench v3.2 results and reported scores

Reported benchmark scores · LLM Stats

Reported scores: 1

ModelOrganizationReported valueReportedEvidence
Grok 4.6xAI0.6992026-08-12evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite CursorBench v3.2?

Related agents, code benchmarks