Skip to main content
benchlm.ai

CursorBench

Cursor's current first-party benchmark for ambiguous, multi-file coding-agent tasks from real Cursor sessions.

Data verified

Benchmark score on CursorBench — July 9, 2026

BenchLM mirrors the published score view for CursorBench. Claude Fable 5 leads the public snapshot at 70.5% , followed by GPT-5.6 Sol (67.2%) and Grok 4.5 (66.7%). BenchLM does not use these results to rank models overall.

1Closed

Claude Fable 5

Anthropic

claude-fable-5

70.5%
Overall 91Context 1M+
2Closed

GPT-5.6 Sol

OpenAI

gpt-5-6-sol

67.2%
Overall —Context 1M
3Closed

Grok 4.5

xAI

grok-4-5

66.7%
Overall —Context 500K
12 modelsCodingRefreshingDisplay onlyUpdated July 9, 2026

The published CursorBench snapshot is tightly clustered at the top: Claude Fable 5 sits at 70.5%, while the third row is only 3.8 points behind. The broader top-10 spread is 15.5 points, so the benchmark still separates strong models even when the leaders cluster.

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

About CursorBench

Year

2026

Tasks

Harder long-horizon agentic coding tasks

Format

Cursor agent-loop evaluation

Difficulty

Professional agentic software engineering

Cursor reports CursorBench v3.2 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 and flags Cursor's published Grok 4.5 contamination caveat in provenance.

CursorBench 3.2

BenchLM freshness & provenance

Version

cursorBench32

Refresh cadence

Static

Staleness state

Refreshing

Question availability

Public benchmark set

RefreshingDisplay 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 (12 models)

1
Claude Fable 5claude-fable-5
70.5%
2
GPT-5.6 Solgpt-5-6-sol
67.2%
3
Grok 4.5grok-4-5
66.7%
4
GPT-5.6 Terragpt-5-6-terra
64.9%
5
Claude Opus 4.8claude-opus-4-8
62.3%
6
Claude Sonnet 5claude-sonnet-5
61.5%
7
GPT-5.6 Lunagpt-5-6-luna
61.1%
8
GPT-5.5gpt-5-5
58.4%
9
Composer 2.5composer-2-5
56.1%
10
GLM-5.2glm-5-2
55.0%
11
Kimi K2.7 Codekimi-k2-7-code
49.7%
12
Gemini 3.5 Flashgemini-3-5-flash
48.8%

FAQ

What does CursorBench measure?

Cursor's current first-party benchmark for ambiguous, multi-file coding-agent tasks from real Cursor sessions.

Which model scores highest on CursorBench?

Claude Fable 5 by Anthropic currently leads with a score of 70.5% on CursorBench.

How many models are evaluated on CursorBench?

12 AI models have been evaluated on CursorBench on BenchLM.

Compare Top Models on CursorBench

Claude Fable 5 vs GPT-5.6 SolGPT-5.6 Sol vs Grok 4.5Grok 4.5 vs GPT-5.6 TerraGPT-5.6 Terra vs Claude Opus 4.8
Last updated: July 9, 2026 · BenchLM version cursorBench32

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.