Skip to main content
BenchLM
Data

CursorBench

Data verified

Cursor's first-party benchmark for ambiguous, multi-file coding-agent tasks drawn from real Cursor sessions, currently on the 4.0 task set.

Top models on CursorBench — November 19, 2026

As of November 19, 2026, Gemini 4 Carbon leads the CursorBench leaderboard with 60.4% , followed by Claude Fable 5.2 (60.0%) and Claude Opus 5.5 (57.8%).

21 modelsCoding10% of Coding reference weightCurrentUpdated November 19, 2026

Leaderboard (21 models)

CursorBench leaderboard
RankModel / configurationScoreParameters (B)Open / closed
1Gemini 4 CarbonGoogleRun by CursorBench
60.4%
Not reportedClosed
2Claude Fable 5.2AnthropicRun by CursorBench
60.0%
Not reportedClosed
3Claude Opus 5.5AnthropicRun by CursorBench
57.8%
Not reportedClosed
4Claude Sonnet 5.5AnthropicRun by CursorBench
55.5%
Not reportedClosed
5Gemini 4 HydrogenGoogleRun by CursorBench
54.3%
Not reportedClosed
6Gemini 4 ArgonGoogleRun by CursorBench
52.9%
Not reportedClosed
7Claude Fable 5.1AnthropicRun by CursorBench
51.8%
Not reportedClosed
8Muse WonderMetaRun by CursorBench
50.4%
Not reportedClosed
9Claude Haiku 5.5AnthropicRun by CursorBench
48.4%
Not reportedClosed
10DeepSeek V4.1 Flash 1017DeepSeekRun by CursorBench
47.7%
Not reportedOpen
11Claude Opus 5AnthropicRun by CursorBench
46.6%
Not reportedClosed
12Grok 4.7xAIRun by CursorBench
46.3%
Not reportedClosed
13GLM-5.3Z.AIRun by CursorBench
42.6%
Not reportedOpen
14GPT-5.6 SolOpenAIRun by CursorBench
41.7%
Not reportedClosed
15Muse Spark 1.3MetaRun by CursorBench
41.6%
Not reportedClosed
16Grok 4.6xAIRun by CursorBench
41.4%
Not reportedClosed
17GPT-5.6 TerraOpenAIRun by CursorBench
41.3%
Not reportedClosed
18GLM-5.3-FlashZ.AIRun by CursorBench
36.8%
Not reportedOpen
19GPT-5.6 LunaOpenAIRun by CursorBench
35.9%
Not reportedClosed
20Claude Sonnet 5AnthropicRun by CursorBench
34.1%
Not reportedClosed
21Composer 2.5CursorRun by CursorBench
27.7%
Not reportedClosed
  • Lab-reported
  • Benchmark-run
  • Independent
What the labels mean

According to BenchLM.ai, Gemini 4 Carbon leads the CursorBench benchmark with a score of 60.4%, followed by Claude Fable 5.2 (60.0%) and Claude Opus 5.5 (57.8%). The top models are clustered within 2.6 points, suggesting this benchmark is nearing saturation for frontier models.

21 models have been evaluated on CursorBench. The benchmark falls in the Coding category. BenchAlign v5.8 gives CursorBench 10% of the Coding reference weight, so it moves the Coding leaderboard and the overall ranking. Reference weights are relative weights in the calibrated model, not fixed shares of a score.

About CursorBench

Year

2026

Tasks

Long-horizon multi-file agentic coding tasks

Format

Cursor agent-loop evaluation

Difficulty

Professional agentic software engineering

Cursor published the CursorBench 4.0 task set on September 10, 2026, adding long-horizon edit, refactor, investigation, intent-understanding, job-management, and design-adherence problems; 4.0 scores are not comparable with the retired 3.2 set. BenchLM maps the highest published effort tier for each model. Since November 12, 2026, 4.0 is the CursorBench instrument in the coding score; the frozen CursorBench 3.2 rows stay on model pages for reference.

Freshness and provenance

Version

CursorBench 4.0

Refresh cadence

Continuous

Staleness state

Current

Question availability

Tasks private; drawn from real Cursor sessions

Current

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.

Questions

What does CursorBench measure?

Cursor's first-party benchmark for ambiguous, multi-file coding-agent tasks drawn from real Cursor sessions, currently on the 4.0 task set.

Which model scores highest on CursorBench?

Gemini 4 Carbon by Google currently leads with a score of 60.4% on CursorBench.

How many models are evaluated on CursorBench?

21 AI models have published results on CursorBench in the BenchLM catalog.

Last updated: November 19, 2026 · BenchLM version CursorBench 4.0

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 7,000+ subscribers.

One email each week. Unsubscribe anytime.