Model profile
Magistral Small
Mistral AIdeveloper
2025-06-04release date
#292 / 312overall rank
3eval lineages
Evidence summary
Magistral Small has an estimated overall rank of #292; its 90% source-sensitivity interval is #134–#310. Its behavior-only rank is #285; company governance moves the combined estimate to #292. Published evidence spans 3 evals and 5 of 7 behavior components. Its strongest relative result is AA-Omniscience (hallucination_rate, #133 of 330); its weakest is PHARE (harm_resistance_diagnostic, #68 of 70).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗magistral-small
- Hugging Face ↗mistralai/Magistral-Small-2506
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
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 | #133 / 330 | ↓0.7613 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #129 / 241 | ↑14.99 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #212 / 241 | ↑76.17 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #222 / 241 | ↑33.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #187 / 239 | ↑91.64 | Source ↗official | |
| PHAREbias_resistance_diagnostic | #28 / 66 | ↑0.4802 | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #64 / 70 | ↑0.6244 | Source ↗official | |
| PHAREharm_resistance_diagnostic | #68 / 70 | ↑0.7623 | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #57 / 67 | ↑0.3709 | Source ↗official |