Model profile
Phi 2
Microsoftdeveloper
#237 / 312overall rank
3eval lineages
Evidence summary
Phi 2 has an estimated overall rank of #237; its 90% source-sensitivity interval is #85–#300. Its behavior-only rank is #241; company governance moves the combined estimate to #237. Published evidence spans 3 evals and 3 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #44 of 241); its weakest is Microsoft Phi Safety Panels (harmful_continuation, #10 of 10).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Microsoft Phi-2 ↗Exact model document · huggingface · official repository
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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #44 / 241 | ↑31.52 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #162 / 241 | ↑85.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #239 / 241 | ↑21.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #237 / 239 | ↑56.36 | Source ↗official | |
| Microsoft Phi Safety Panelsharmful_continuation | #10 / 10 | ↓0.029 | Source ↗official | |
| Microsoft Phi Safety Panelsharmful_summarization | #9 / 10 | ↓0.144 | Source ↗official | |
| Microsoft Phi Safety Panelsjailbreak | #8 / 10 | ↓0.15 | Source ↗official | |
| Microsoft Phi Safety Panelsthird_party_harm | #2 / 10 | ↓0.24 | Source ↗official | |
| Open LLM Safety Indexjailbreakbench_safety_rate | #16 / 21 | ↑0.1333 | Source ↗official | |
| Open LLM Safety Indexstrongreject_safety_rate | #19 / 21 | ↑0 | Source ↗official |