Model profile
Phi-4 Multimodal Instruct
Evidence summary
Safety. Phi-4 Multimodal Instruct does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 1 of 7 components. Its strongest relative result is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #49 of 104); its weakest is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #49 of 104).
Freedom. Phi-4 Multimodal Instruct has an estimated Freedom rank of #440; its 90% source-sensitivity interval is #280–#567. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is Cisco AI Defense Rolling Single-Turn Leaderboard (single_turn_attack_success_rate, #56 of 104); its weakest is SpeechMap model completion (complete_pct, #99 of 181).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗microsoft/Phi-4-multimodal-instruct
- OpenRouter ↗microsoft/phi-4-multimodal-instruct
Finetunes
Direct finetunes linked to this canonical base model. Quantized and repackaged derivatives are excluded.
huihui-ai/Phi-4-multimodal-instruct-abliterated ↗Direct non-quantized finetune documented by Hugging Face metadata
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #49 / 104 | ↓35.59 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #56 / 104 | ↑35.59 | Source ↗official | |
| SpeechMap model completioncomplete_pct | #99 / 181 | ↑54.3 | Source ↗official |