Phi-4
MicrosoftMicrosoft's 14B dense small language model, announced December 2024 and fully released the following month, trained on 9.8 trillion tokens of heavily curated and synthetic data. It is the clearest expression of the small-models-with-high-quality-data thesis, and the line has been extended with mini, multimodal, reasoning and reasoning-vision variants.
Scores base Phi-4 14B; the reasoning variants are separate SKUs. The curated training data is not released, which the openness axis weighs alongside the distribution terms. Verified 2026-08-13 via the microsoft/phi-4 model card and the Artificial Analysis model page.
Openness
3 high confidence- weights
- open(MIT)
- data
- closed
- code
- closed
- license
- MIT(OSI)
MIT weights, which is genuinely permissive with no use restrictions, but neither the training corpus nor the training pipeline is published - Microsoft describes the synthetic data mix without releasing it. So 3, open weights: the artifact is free to use and the recipe is not reproducible. Reaching 4 or 5 would need the data or the pipeline, not a more permissive license.
- https://huggingface.co/api/models/microsoft/phi-4 recorded 2026-08-13
card license `mit`, `gated: false`, `private: false`, safetensors weight files, 662,805 downloads and 2,290 likes.
- https://huggingface.co/microsoft/phi-4 recorded 2026-08-13
Model card - "phi-4 is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets"; Training data 9.8T tokens. The mixture is described, not released, and no training pipeline is linked.
- https://the-decoder.com/microsoft-releases-full-phi-4-model-with-weights-under-mit-license/ recorded 2026-08-13
Microsoft released the full Phi-4 weights on Hugging Face under the MIT license
- https://venturebeat.com/ai/microsoft-makes-powerful-phi-4-model-fully-open-source-on-hugging-face recorded 2026-06-04
VentureBeat coverage of the Phi-4 MIT release; the host answers HTTP 429, so it is not a live source for this axis.
Adoption
3 high confidence626,702 downloads in the trailing 30 days for the single declared artifact microsoft/phi-4, which bands at level 3 (100K-1M) on the model adoption scale.
- https://huggingface.co/api/models/microsoft/phi-4 recorded 2026-08-13
626,702 downloads in the trailing 30 days for microsoft/phi-4
Capability
3 high confidence14B model with outsized math/reasoning: ~56.1% on graduate-level (GPQA-style) science questions, 80.4% on competition math, strong AMC results; reportedly beats GPT-4 (its teacher) on some STEM. Strong-for-size but a small/older model vs 2026 frontier. Artificial Analysis places Phi-4 at #47 of 74 on its Intelligence Index - a mid-table position on the 2026 comparison set, which is what a 3 encodes.
- https://the-decoder.com/microsoft-releases-full-phi-4-model-with-weights-under-mit-license/ recorded 2026-08-13
~56.1% on graduate-level science questions and 80.4% on competition math, both present
- https://artificialanalysis.ai/models/phi-4 recorded 2026-08-13
Phi-4 model page - Intelligence "# 47 / 74", 5 on the Artificial Analysis Intelligence Index, listed as an open-weights model released December 2024.
Verified 2026-08-13