SWE-bench Verified hard subset (Meta)

Muse Spark 42.9% Only in system cards

Agents fix the hardest SWE-bench Verified issues. Meta uses about 42 tasks and a 50% indicative threshold for AI R&D risk.

Meta's own hard subset. It may differ from Anthropic's SWE-bench Verified hard subset.

Made by Meta Released Apr 2026 Fixing real repositories All tasks public Last in a system card Jun 2026 Last model added Jun 2026

Level: Expert Specialists with years of training, often over hours of work
Scored: Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers: Code A program or patch run against tests.

Model scored in lab cards

System card reports it, from 1 lab

Muse Spark leads with 42.9%

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

42.9 Muse Spark

1 Muse Spark 42.9%

#	Model	Score	Setting	Date	Source
1	Muse Spark	42.9%		Jun 2026	Model card

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

Labs report it only in system cards

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.

One system card reports it

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
12 Jun 2026	Muse Spark system card	42.9	SWE-Bench Verified (hard subset) (2.3.1.1 text)	AI R&D risk

Muse Spark leads with 42.9%

Scores over time

Labs report it only in system cards

One system card reports it

More in Coding