Model profile
Muse Spark 1.2
Evidence summary
Safety. Muse Spark 1.2 has an estimated Safety rank of #17; its 90% source-sensitivity interval is #18–#67. Its behavior-only rank is #15; company governance moves the combined estimate to #17. Published Safety evidence spans 8 eval lineages and 5 of 7 components. Its strongest relative result is SpeciEval (belief_animal_sentience, #1 of 131); its weakest is Vals AI Cheating Audit (biomystery_bench_cheating_attempt_rate_pct, #7 of 9).
Freedom. Muse Spark 1.2 has an estimated Freedom rank of #249; its 90% source-sensitivity interval is #67–#543. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SM-Bench (adversarial, #31 of 92); its weakest is SM-Bench (overfit, #39 of 92).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗muse-spark-1-2
- OpenRouter ↗meta/muse-spark-1.2
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #45 / 358 | ↓0.3329 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #38 / 122 | ↑0.495 | Source ↗official | |
| Claude system cards — Gray Swan Q1+Q2 indirect prompt injection k=15attack_success_probability_k15_pct | #7 / 12 | ↓24.2 | Source ↗official | |
| Google Gemini 3.8 launch — Gray Swan indirect prompt injection k=15attack_success_probability_k15_pct | #8 / 15 | ↓24.2 | Source ↗official | |
| SM-Benchadversarial | #59 / 92 | ↑80 | Source ↗official | |
| SM-Benchambiguous_interpretation | #5 / 92 | ↑93.75 | Source ↗official | |
| SM-Benchanti_hallucination | #10 / 92 | ↑98.95 | Source ↗official | |
| SM-Bencheq_boundaries | #36 / 92 | ↑67.42 | Source ↗official | |
| SM-Benchoverfit | #39 / 92 | ↑80.33 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #1 / 131 | ↑7 | Source ↗official | |
| SpeciEvalland_animal_4ns | #72 / 131 | ↓4.58 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #40 / 131 | ↓4.58 | Source ↗official | |
| SpeciEvalspeciesism | #73 / 131 | ↓2.08 | Source ↗official | |
| Vals AI Cheating Auditbiomystery_bench_cheating_attempt_rate_pct | #7 / 9 | ↓7.037 | Source ↗official | |
| Vals Teen Conversation Safetyshare_flagged_pct | #1 / 8 | ↓9.722 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.