CursorBench 3.2

Claude Fable 5.1 73.4% leads since Sep 2026 In use

Agents do ambiguous multi-file coding tasks from real Cursor sessions in Cursor's harness. Version 3.2 added instruction following and advanced tool use problems. Agentic graders score correctness.

Cursor's changelog dates it 2026-07-08. It changed the task mix, so scores do not compare with 3.1. xAI's Grok 4.6 card and Anthropic's Fable 5.1 card name this version.

Made by Cursor Released Jul 2026 Fixing real repositories Tasks kept private Last in a launch post Sep 2026 Last model added Sep 2026

Level: Expert Specialists with years of training, often over hours of work
Scored: Graded by a model A language model scores each response, usually against a rubric.
Answers: Code A program or patch run against tests.

Leaderboard cursor.com

Models scored in lab cards

Launch posts list it, from 2 labs

System cards report it, from 2 labs

Claude Fable 5.1 leads with 73.4%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

Bars Table

1 Claude Fable 5.1 73.4%
2 Grok 4.6 70.8%

#	Model	Score	Setting	Date	Source
1	Claude Fable 5.1	73.4%		Sep 2026	Model card
2	Grok 4.6	70.8%		Aug 2026	Model card

2 models have held number one since its release in Jul 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

xAI Anthropic

Lab claims Replaced by 4.0, Sep 2026

Claude Fable 5.1 73.4%

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card Best so far

2 labs put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

xAI

Anthropic

Date	Launch post	Score	As the post writes it
1 Sep 2026	Claude Fable 5.1	73.4	Agentic coding CursorBench 3.2.0
12 Aug 2026	Grok 4.6	69.9	CursorBench v3.2

2 system cards report it, from 2 labs

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

Date	Document	Score	As the document writes it	Section
1 Sep 2026	Claude Fable 5.1 system card	73.4	CursorBench 3.2.0 at max effort, measured by Cursor; 68.0% at medium effort (8.8)	Capabilities
12 Aug 2026	Grok 4.6 model card	70.8	CursorBench 3.2, xhigh, Cursor agent harness, run by Cursor (2.1 text). High = 69.9%	Capabilities

Versions

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

Cursor xAI Anthropic

CursorBench 4.0 5 leaders