Skip to main content
BenchLM
Advertise

Benchmark profile

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 29, 2026

BenchLM mirrors the published score view for CursorBench. Claude Fable 5 leads the public snapshot at 70.5% , followed by Claude Opus 5 (70.0%) and GPT-5.6 Sol (67.2%). BenchLM does not use these results to rank models overall.

1Closed

Claude Fable 5

Anthropic

claude-fable-5

70.5%
Overall 82.75Context 1M+
2Closed

Claude Opus 5

Anthropic

claude-opus-5

70.0%
Overall 82.81
3Closed

GPT-5.6 Sol

OpenAI

gpt-5-6-sol

67.2%
Overall 81.39Context 1M
14 modelsCodingRefreshingDisplay onlyUpdated July 29, 2026

Benchmark score table (14 models)

Score
1
Claude Fable 5Anthropic · Closed
70.5%
2
Claude Opus 5Anthropic · Closed
70.0%
3
GPT-5.6 SolOpenAI · Closed
67.2%
4
Grok 4.5xAI · Closed
66.7%
5
GPT-5.6 TerraOpenAI · Closed
64.9%
6
Claude Opus 4.8Anthropic · Closed
62.3%
7
Claude Sonnet 5Anthropic · Closed
61.5%
8
GPT-5.6 LunaOpenAI · Closed
61.1%
9
GPT-5.5OpenAI · Closed
58.4%
10
Composer 2.5Cursor · Closed
56.1%
11
GLM-5.2Z.AI · Open weight
55.0%
12
Gemini 3.6 FlashGoogle · Closed
53.5%
13
Kimi K2.7 CodeMoonshot AI · Open weight
49.7%
14
Gemini 3.5 FlashGoogle · Closed
48.8%

The published CursorBench snapshot places Claude Fable 5 first at 70.5%. The third row is 3.3 points behind. The broader top-10 range is 14.4 points, so the table still separates the published systems.

14 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.

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?

14 AI models have been evaluated on CursorBench on BenchLM.

Compare Top Models on CursorBench

Claude Fable 5 vs Claude Opus 5Claude Opus 5 vs GPT-5.6 SolGPT-5.6 Sol vs Grok 4.5Grok 4.5 vs GPT-5.6 Terra
Last updated: July 29, 2026 · BenchLM version cursorBench32

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.