StrongREJECT v2 (Meta)
Muse Spark 1.1 0.50% leads since July 2026 Models face a cascade of jailbreak attacks on disallowed behaviors adapted from StrongREJECT plus internal ones. Reports attack success rate.
Meta variant of public StrongREJECT with internally curated behaviors and a multi-turn LLM attacker.
- Made by
- Meta
- Kind
- Jailbreaks and prompt injection
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Kept private
- Strongest model tested
- Muse Spark 1.3 #26 on the capability index
- Last in a launch post
- October 2026
- Last model added
- October 2026
3 models share the top score of 0.50%
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.
- 1 Muse Spark 1.1 0.50%
- 2 Muse Spark Open 0.50%
- 3 Muse Spark 1.3 0.50%
- 4 Muse Spark 44.6%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Muse Spark 1.1 | 0.50% | Jul 2026 | Lab model card | |
| 2 | Muse Spark Open | 0.50% | Oct 2026 | Lab model card | |
| 3 | Muse Spark 1.3 | 0.50% | Oct 2026 | Lab model card | |
| 4 | Muse Spark | 44.6% | Jun 2026 | Lab model card |
2 models have held number one in labs’ own numbers since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
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.
Source: Labs’ model cards
One lab 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.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Oct 15, 2026 | Muse Spark Open | 0.5 | StrongREJECT v2 (adaptive), lower is better |
3 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 |
|---|---|---|---|---|
| Oct 23, 2026 | Muse Spark 1.3 system card | 0.5 | StrongREJECT v2 ASR averaged over single-turn and multi-turn, Muse Spark 1.3 (API) max (Table 2, Figure 21) | Robustness |
| Jul 9, 2026 | Muse Spark 1.1 system card | 0.5 | StrongREJECT v2 ASR (Table 2 scorecard, Figure 24) | Robustness |
| Jun 12, 2026 | Muse Spark system card | 44.6 | StrongREJECT v2 ASR at end of cascaded attack pipeline, Muse Spark (Table 2, Figure 27) | Robustness |
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6% - Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts.
Gemini 4 Carbon 0% - DistressBench In use Models reply as a chatbot to 718 simulated users in psychological crisis, in single-turn and multi-turn chats. Three judge models score replies against clinician-written rubrics. Muse Spark 1.2 88.4%
- Lakera B3 (Backbone Breaker Benchmark) In use Crowdsourced prompt-injection attacks hit backbone LLMs inside agent threat snapshots at three defense levels. The score is attack resistance, 100 minus the board's vulnerability percentage. Claude Opus 4.5 89%
- IHEval In use Models face conflicts between system, user and tool instructions. Reports a composite score for following the higher-priority instruction. GPT-4o 70%