Model profile
Phi 4 Mini
Microsoftdeveloper
#282 / 312overall rank
4eval lineages
Evidence summary
Phi 4 Mini has an estimated overall rank of #282; its 90% source-sensitivity interval is #166–#301. Its behavior-only rank is #287; company governance moves the combined estimate to #282. Published evidence spans 4 evals and 4 of 7 behavior components. Its strongest relative result is AA-Omniscience (hallucination_rate, #143 of 330); its weakest is Vectara HHEM Factual Consistency (factual_consistency_rate, #94 of 94).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗phi-4-mini
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 | #143 / 330 | ↓0.7799 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #60 / 104 | ↓42.72 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #150 / 241 | ↑13.7 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #153 / 241 | ↑86.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #140 / 241 | ↑60.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #114 / 239 | ↑96.45 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #94 / 94 | ↑76.5 | Source ↗official |