Model profile
Phi 4 Reasoning Plus
2025-04-17release date
2eval lineages
Evidence summary
Published evidence spans 2 evals and 5 of 7 behavior components. Its strongest relative result is UAVBench safety-critical decision recognition (ethical_safety_critical_accuracy, #7 of 27); its weakest is FlagEval Safety and Values (a2_qualified_rate, #13 of 18).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗microsoft/Phi-4-reasoning-plus
- OpenRouter ↗microsoft/phi-4-reasoning-plus
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
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 | Better | Source |
|---|---|---|---|---|---|
| FlagEval Safety and Valuesa1_qualified_rate | #7 / 18 | 81.55 | ↑ higher | Source ↗official | |
| FlagEval Safety and Valuesa2_qualified_rate | #13 / 18 | 78.31 | ↑ higher | Source ↗official | |
| FlagEval Safety and Valuesa3_qualified_rate | #6 / 18 | 87.76 | ↑ higher | Source ↗official | |
| FlagEval Safety and Valuesa4_qualified_rate | #11 / 18 | 87.95 | ↑ higher | Source ↗official | |
| FlagEval Safety and Valuesa5_qualified_rate | #13 / 18 | 69.65 | ↑ higher | Source ↗official | |
| UAVBench safety-critical decision recognitionethical_safety_critical_accuracy | #7 / 27 | 0.735 | ↑ higher | Source ↗official |