BioTIER
Muse Wonder Full 98.7% leads since Oct 2026 Only in system cards Safeguarded model configurations receive harmful and benign biology requests. Scored on refusing requests designated for refusal and allowing benign ones.
Run by SecureBio. Counts full blocks and model-jury graded soft refusals.
- 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
- Open-ended Free-form text, documents, designs or media judged as a whole.
Muse Wonder Full leads with 98.7%
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 Wonder Full 98.7%
- 2 Muse Spark 98%
- 3 Muse Spark 1.1 97.7%
- 4 Muse Spark 1.3 97.4%
- 5 GPT-6 Astra 82.9%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Muse Wonder Full | 98.7% | Oct 2026 | Model card | |
| 2 | Muse Spark | 98% | Jun 2026 | Model card | |
| 3 | Muse Spark 1.1 | 97.7% | Jul 2026 | Model card | |
| 4 | Muse Spark 1.3 | 97.4% | Oct 2026 | Model card | |
| 5 | GPT-6 Astra | 82.9% | Sep 2026 | Model card |
2 models have held number one since its release in Sep 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
The best score passed 85% in Jun 2026
All the scores we have, one dot each, so a model tested at several settings appears more than once.
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.
5 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 |
|---|---|---|---|---|
| 23 Oct 2026 | Muse Spark 1.3 system card | 97.4 | BioTIER v1 (English) refusal rate, Muse Spark 1.3 (API) with system mitigations (Table 2, Figure 5). Multilingual 96.9, adversarial 95.3 | Bio and chem risk |
| 12 Oct 2026 | Muse Wonder Full model card | 98.7 | BioTIER English refusal rate (CBRN Safety Evaluations table, section 4). Multilingual 98.7, adversarial 98.2 | Bio and chem risk |
| 3 Sep 2026 | GPT-6 Astra system card | 82.9 | SecureBio BioTIER, safeguarded configuration refused requests designated for refusal (benign allowed 95.3%) (10.2.4.2) | Safety |
| 9 Jul 2026 | Muse Spark 1.1 system card | 97.7 | Refusals: BioTIER v1 refusal rate (Table 2, Figure 6) | Bio and chem risk |
| 12 Jun 2026 | Muse Spark system card | 98 | Refusals: BioTIER refusal rate, deployed system (Table 2, Figure 9) | Bio and chem risk |
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% - AgentDojo In use Agents do tool-use tasks while tools and data carry prompt injections. Attack success rate counts hijacked runs. Grok 4 Fast 0%
- MASK In use Measures whether a model contradicts its own elicited beliefs under pressure to lie. Honesty separated from accuracy. Muse Spark Open 98.1%
- 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. GPT-6 Astra 8.50%
- Agentic misalignment suite (Anthropic) In use Agents in simulated company settings face threats or goal conflicts that invite blackmail, leaking or sabotage. Score is the misaligned action rate. Claude Sonnet 4.5 0%