Model profile
Magistral Medium
Mistral AIdeveloper
2025-06-10release date
#163 / 309overall rank
6eval lineages
Evidence summary
Magistral Medium has an estimated overall rank of #163; its 90% source-sensitivity interval is #77–#286. Its behavior-only rank is #153; company governance moves the combined estimate to #163. Published evidence spans 6 evals and 6 of 7 behavior components. Its strongest relative result is FlagEval Safety and Values (a3_qualified_rate, #3 of 18); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #222 of 241).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗magistral-medium
- Official model documentation ↗Family-level model document · mistral · first party
- Release source ↗curated outward evidence
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 | #74 / 328 | ↓0.5966 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #121 / 241 | ↑15.76 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #182 / 241 | ↑83.17 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #222 / 241 | ↑33.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #185 / 239 | ↑91.82 | Source ↗official | |
| FlagEval Safety and Valuesa1_qualified_rate | #12 / 18 | ↑79.01 | Source ↗official | |
| FlagEval Safety and Valuesa2_qualified_rate | #12 / 18 | ↑78.73 | Source ↗official | |
| FlagEval Safety and Valuesa3_qualified_rate | #3 / 18 | ↑89.28 | Source ↗official | |
| FlagEval Safety and Valuesa4_qualified_rate | #7 / 18 | ↑89.15 | Source ↗official | |
| FlagEval Safety and Valuesa5_qualified_rate | #3 / 18 | ↑74.27 | Source ↗official | |
| HUMAINE Trust, Ethics and Safetytrust_ethics_safety_score | #36 / 54 | ↑26.12 | Source ↗official | |
| MASKlying_probability_pct | #31 / 53 | ↓43.5 | Source ↗official | |
| PHAREbias_resistance_diagnostic | #25 / 66 | ↑0.5075 | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #49 / 70 | ↑0.6819 | Source ↗official | |
| PHAREharm_resistance_diagnostic | #60 / 70 | ↑0.8452 | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #41 / 67 | ↑0.4561 | Source ↗official |