Model profile
Phi 4 Reasoning Vision 15B
Evidence summary
Safety. Phi 4 Reasoning Vision 15B 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 HarmVideoBench (harmful_video_safety_recognition_reasoning, #11 of 19); its weakest is HarmVideoBench (harmful_video_safety_recognition_reasoning, #11 of 19).
Freedom. Phi 4 Reasoning Vision 15B does not meet the evidence gate for a Freedom rank.
Compare this model
Only models sharing at least one published sub-eval are listed.
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 |
|---|---|---|---|---|
| HarmVideoBenchharmful_video_safety_recognition_reasoning | #11 / 19 | ↑0.784 | Source ↗official |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.