Model profile
Muse Spark
Metadeveloper
2026-04-08release date
#133 / 309overall rank
4eval lineages
Evidence summary
Muse Spark has an estimated overall rank of #133; its 90% source-sensitivity interval is #13–#293. Its behavior-only rank is #136; company governance moves the combined estimate to #133. Published evidence spans 4 evals and 3 of 7 behavior components. Its strongest relative result is FORTRESS (average_risk_score, #18 of 49); its weakest is Arena Factuality — Text Arena (factuality-only weighting) (factuality_bt_rating, #110 of 112).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗muse-spark
- Official model page ↗Exact model document · Meta · first party
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #187 / 328 | ↓0.8419 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #110 / 112 | ↑1384.0 | Source ↗official | |
| FORTRESSaverage_risk_score | #18 / 49 | ↓20.22 | Source ↗official | |
| Gray Swan indirect prompt injection (15 attempts)attack_success_probability_k15_pct | #6 / 13 | ↓16.5 | Source ↗official |