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 — June 2, 2026

BenchLM mirrors the published score view for CursorBench v3.1. Claude Opus 4.7 (Adaptive) leads the public snapshot at 64.8% , followed by Composer 2.5 (63.2%) and GPT-5.5 (59.2%). BenchLM does not use these results to rank models overall.

7 modelsCodingCurrentDisplay onlyUpdated June 2, 2026

The published CursorBench v3.1 snapshot is tightly clustered at the top: Claude Opus 4.7 (Adaptive) sits at 64.8%, while the third row is only 5.6 points behind. The broader top-10 spread is 32.9 points, so the benchmark still separates strong models even when the leaders cluster.

7 models have been evaluated on CursorBench v3.1. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. CursorBench v3.1 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

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 on its public evals page for ambiguous, multi-file tasks from real Cursor sessions. 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 (7 models)

1
64.8%
2
63.2%
3
59.2%
4
52.2%
5
49.8%
6
47.6%
7
31.9%

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?

Claude Opus 4.7 (Adaptive) by Anthropic currently leads with a score of 64.8% on CursorBench v3.1.

How many models are evaluated on CursorBench v3.1?

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

Last updated: June 2, 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.