CursorBench 3.1

Claude Fable 5 72.9% leads since June 2026

Fading

Agents do ambiguous multi-file coding tasks from real Cursor sessions in Cursor's harness. Version 3.1 added codebase understanding, bug finding, planning and code review problems. Agentic graders score correctness.

Cursor's changelog dates it May 19th, 2026 and says it also improved grading for some edit tasks. Cursor says 3.1 scores should be compared only within the same version.

Made by: Cursor
Released: May 2026
Kind: Fixing real repositories
Level: Expert
Scored: Graded by a model
Answers: Code
Tasks: Kept private

Strongest model tested: Claude Fable 5 #11 on the capability index
Last in a launch post: May 2026, dropped for a newer version
Last model added: June 2026

Models scored in lab cards

Launch posts list it, from 2 labs

System cards report it, from 1 lab

Claude Fable 5 leads with 72.9% among models released by June 2026

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

The newest model with a score here came out in June 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

Source: Labs’ model cards

#	Model	Score	Date	Source
1	Claude Fable 5	72.9%	Jun 2026	Lab model card
2	Claude Opus 4.7	70%	Apr 2026	Lab model card
3	Composer 2.5	63.2%	May 2026	Lab model card
4	Composer 2	61.3%	Mar 2026	Lab model card
5	Claude Sonnet 5	61.2%	Jun 2026	Lab model card

2 models have held number one in labs’ own numbers since its release in May 2026

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

Anthropic

Lab claims Replaced by 3.2, Jul 2026

Claude Fable 5 72.9%

Source: Labs’ model cards

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

Source: Labs’ model cards

Labs headline it less often now, last in May 2026

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.

Cursor

Anthropic

Date	Launch post	Score	As the post writes it
May 18, 2026	Composer 2.5	63.2	CursorBench v3.1 (harder tasks)
Apr 16, 2026	Claude Opus 4.7	70	CursorBench, 70% at high effort
Mar 19, 2026	Composer 2	61.3	CursorBench

2 system cards report it, from 1 lab

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
Jun 30, 2026	Claude Sonnet 5 system card	61.2	CursorBench at max effort, measured by Cursor, version not stated (xhigh 59.0%, high 57.0%) (8.5, Figure 8.5.A)	Capabilities
Jun 9, 2026	Claude Fable 5 system card	72.9	CursorBench at max effort, measured and reported by Cursor in its production harness, version not stated (8.7, Figure 8.7.A)	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.