Microsoft · USA · Released 2024-12

Phi-4

Microsoft's 14B small language model trained on curated + synthetic data — punches far above its weight on reasoning.

Official site

Access

open-weights

Context

16,000 tokens

Modalities

text

Languages

English-focused

Benchmark scores

MMLU

84.8%

Massive Multitask Language Understanding

GPQA

56.1%

Graduate-level science QA (Diamond)

HumanEval

82.6%

Python code completion

SWE-bench

N/A

Real GitHub issue resolution (Verified)

LiveCodeBench

N/A

Contamination-free coding

AIME

N/A

American Invitational Mathematics Exam

MMMU

N/A

Multimodal college-level reasoning

MATH

80.4%

Competition-level math word problems

Scores as reported by the vendor or leading public leaderboards. "N/A" means the score has not been publicly disclosed for this metric.

Explain like I'm 5

Small but surprisingly smart — runs on modest hardware.

Key features

14B params
Synthetic-data training
Open weights

Strengths

Strong reasoning for size
Cheap to run

Limitations

Small context
English-focused

Best for

Edge deploymentFine-tuning base

Related models

OpenAI

GPT-5

OpenAI's flagship reasoning + multimodal model with a unified router that switches between fast and deep-thinking modes.

Anthropic

Claude Sonnet 4.5

Anthropic's best coding + agentic model, purpose-built for long-horizon computer-use and software engineering tasks.

Google DeepMind

Gemini 2.5 Pro

Google's most capable model with native 1M-token context and full multimodal I/O across text, images, audio and video.

xAI

Grok 4

xAI's frontier reasoning model with real-time X data grounding and a heavy multi-agent variant (Grok 4 Heavy).