Model profile
Muse Spark 1.3
Evidence summary
Safety. Muse Spark 1.3 has an estimated Safety rank of #6; its 90% source-sensitivity interval is #3–#17. Its behavior-only rank is #2; company governance moves the combined estimate to #6. Published Safety evidence spans 4 eval lineages and 3 of 7 components. Its strongest relative result is SpeciEval (belief_animal_sentience, #1 of 123); its weakest is CheatBench direct cheating propensity (software_engineering_cheating_rate_pct, #7 of 8).
Freedom. Muse Spark 1.3 does not meet the evidence gate for a Freedom rank.
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗muse-spark-1-3
- OpenRouter ↗meta/muse-spark-1.3
- Artificial Analysis model profile ↗Exact model document · Artificial Analysis · reliable secondary
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 | #36 / 345 | ↓0.3146 | Source ↗official | |
| CheatBench direct cheating propensitybiology_bioinformatics_cheating_rate_pct | #1 / 8 | ↓11 | Source ↗official | |
| CheatBench direct cheating propensityboard_games_cheating_rate_pct | #5 / 8 | ↓90 | Source ↗official | |
| CheatBench direct cheating propensitycreative_writing_cheating_rate_pct | #1 / 8 | ↓0 | Source ↗official | |
| CheatBench direct cheating propensityknowledge_work_cheating_rate_pct | #3 / 8 | ↓45 | Source ↗official | |
| CheatBench direct cheating propensitymathematical_research_cheating_rate_pct | #3 / 8 | ↓80 | Source ↗official | |
| CheatBench direct cheating propensitymenial_computation_cheating_rate_pct | #2 / 8 | ↓50 | Source ↗official | |
| CheatBench direct cheating propensitymultimodal_cheating_rate_pct | #2 / 8 | ↓52 | Source ↗official | |
| CheatBench direct cheating propensitysoftware_engineering_cheating_rate_pct | #7 / 8 | ↓53 | Source ↗official | |
| CheatBench direct cheating propensitysvg_competition_cheating_rate_pct | #1 / 8 | ↓0 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #1 / 123 | ↑7 | Source ↗official | |
| SpeciEvalland_animal_4ns | #68 / 123 | ↓4.58 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #41 / 123 | ↓4.62 | Source ↗official | |
| SpeciEvalspeciesism | #7 / 123 | ↓1.23 | Source ↗official | |
| TACbase_welfare_rate | #7 / 87 | ↑43.59 | Source ↗self run |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.