Phi-4
READER SUMMARYA 14-billion-parameter dense reasoning model with 16,000-token context, strong mathematical performance and Azure AI Foundry availability under a research release.
Why this model scores 57.1
Phi-4 raises reasoning capability for a compact model and can support tool-using applications, but it is not independently agentic. Initial Foundry and research-license access limits deployment relative to later open releases, while small size raises potential diffusion.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
News tied to Phi-4
The model score of 57.1 rates this model's risk profile. The overall Doom Index of 63.2 measures the recalibrated complete evidence corpus. These values answer different questions.
Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.
Microsoft introduces 14-billion-parameter Phi-4
Microsoft introduced Phi-4, a 14-billion-parameter reasoning model trained with synthetic and curated data and made available through Azure AI Foundry under a research release.
- Full item contribution
- +0.03
- Phi-4 equal share
- +0.03
Model score history
- R1Doom Score 57.1
Initial exact source-backed profile for the December 12 Phi-4 release.
12 Aug 2026