Skip to main content

CursorBench v3.1

Cursor's first-party harder-task benchmark for long-horizon agentic coding behavior inside the Cursor agent loop.

Benchmark score on CursorBench v3.1 — May 20, 2026

BenchLM mirrors the published score view for CursorBench v3.1. Composer 2.5 leads the public snapshot at 63.2%. BenchLM does not use these results to rank models overall.

1 modelsCodingCurrentDisplay onlyUpdated May 20, 2026

About CursorBench v3.1

Year

2026

Tasks

Harder long-horizon agentic coding tasks

Format

Cursor agent-loop evaluation

Difficulty

Professional agentic software engineering

Cursor reports CursorBench v3.1 alongside public Terminal-Bench 2.0 and SWE-bench Multilingual results in the Composer 2.5 launch table. BenchLM tracks it as display-only because it is a first-party benchmark.

BenchLM freshness & provenance

Version

CursorBench v3.1 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Benchmark score table (1 models)

1
63.2%

FAQ

What does CursorBench v3.1 measure?

Cursor's first-party harder-task benchmark for long-horizon agentic coding behavior inside the Cursor agent loop.

Which model scores highest on CursorBench v3.1?

Composer 2.5 by Cursor currently leads with a score of 63.2% on CursorBench v3.1.

How many models are evaluated on CursorBench v3.1?

1 AI models have been evaluated on CursorBench v3.1 on BenchLM.

Last updated: May 20, 2026 · BenchLM version CursorBench v3.1 2026

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.