Unauthorized Code Execution Bench

Muse Spark 1.3 21.1% Only in system cards

A coding agent meets injected instructions to run or fetch malicious artifacts while doing a benign task. Reports attack success rate.

In-house Meta benchmark of 76 tasks over 40 malicious objectives.

Made by Meta Secure code and review Tasks kept private Last in a system card Oct 2026 Last model added Oct 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: Agent task Many steps in a terminal, browser, desktop, app, game or robot.

Model scored in lab cards

System card reports it, from 1 lab

Muse Spark 1.3 leads with 21.1%

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 Muse Spark 1.3 21.1%

#	Model	Score	Setting	Date	Source
1	Muse Spark 1.3	21.1%		Oct 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
23 Oct 2026	Muse Spark 1.3 system card	21.1	Unauthorized Code Execution Bench ASR, Muse Spark 1.3 (API) (Figure 27, caption says pass@3, axis says pass@1)	Robustness

Muse Spark 1.3 leads with 21.1%

Scores over time

Labs report it only in system cards

One system card reports it

More in Cybersecurity