Model profile
Phi 3.5 Moe Instruct
Evidence summary
Phi 3.5 Moe Instruct has an estimated overall rank of #33; its 90% source-sensitivity interval is #7–#161. Its behavior-only rank is #25; company governance moves the combined estimate to #33. Published evidence spans 5 evals and 6 of 7 behavior components. Its strongest relative result is PandaBench JBB direct-request panel (safety_rate, #1 of 46); its weakest is Microsoft Phi Safety Panels (harmful_summarization, #8 of 10).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗microsoft/Phi-3.5-MoE-instruct
- Model card ↗Exact model document · Microsoft · first party
- Release source ↗direct research preview identity date
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 |
|---|---|---|---|---|
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #5 / 32 | ↓8.2 | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #5 / 32 | ↓3.9 | Source ↗official | |
| AILuminate General Purpose AI Chathate | #5 / 32 | ↓2.5 | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #4 / 32 | ↓6.7 | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #6 / 32 | ↓4.5 | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #3 / 32 | ↓4.5 | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #5 / 32 | ↓4.5 | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #3 / 32 | ↓3.7 | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #4 / 32 | ↓4.7 | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #4 / 32 | ↓6.9 | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #4 / 32 | ↓3.7 | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #3 / 32 | ↓5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #129 / 241 | ↑14.99 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #134 / 241 | ↑87.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #95 / 241 | ↑76.11 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #58 / 239 | ↑98.32 | Source ↗official | |
| Large-scale Moral Machine experiment on LLMshuman_choice_distance | #16 / 39 | ↓0.9383 | Source ↗official | |
| Microsoft Phi Safety Panelsharmful_continuation | #2 / 10 | ↓0.004 | Source ↗official | |
| Microsoft Phi Safety Panelsharmful_summarization | #8 / 10 | ↓0.12 | Source ↗official | |
| Microsoft Phi Safety Panelsjailbreak | #2 / 10 | ↓0.11 | Source ↗official | |
| Microsoft Phi Safety Panelsthird_party_harm | #1 / 10 | ↓0.152 | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #1 / 46 | ↑1 | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.