Microsoft: Phi 4
Microsoft • LLM
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
Specifications
Context Window
16K tokens
Input Price/1M
$0.13
Output Price/1M
$0.50
Parameters
—
Speed
42 tok/s
Latency (TTFT)
521ms
Max Output
16K tokens
Benchmarks
Microsoft: Phi 4 results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
Agentic
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Terminal-Bench Hard | 4.0 | 100.0 | — |
Coding
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| SciCode | 26.0 | 100.0 | — |
| LiveCodeBench | 23.0 | 100.0 | Artificial Analysis official API |
| AA Coding Index | 11.2 | 100.0 | Artificial Analysis official API |
Knowledge
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU-Pro | 71.0 | 100.0 | — |
Long Context
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA-LCR | 0.0 | 100.0 | — |
Math
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MATH-500 | 81.0 | 100.0 | Artificial Analysis official API |
| AA Math Index | 18.0 | 100.0 | Artificial Analysis official API |
| AIME 2025 | 18.0 | 100.0 | Artificial Analysis official API |
overall
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| HF Average | 27.5 | 100.0 | HuggingFace Open LLM Leaderboard v2 |
| AA Intelligence Index | 10.4 | 100.0 | Artificial Analysis official API |
Reasoning
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU Pro | 71.4 | 100.0 | Artificial Analysis official API |
| GPQA Diamond | 57.0 | 100.0 | Artificial Analysis official API |
| IFBench | 24.0 | 100.0 | — |
| HLE | 4.0 | 100.0 | — |
Tool Use
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Tau²-Bench | 0.0 | 100.0 | — |
Information
- Release date
- December 12, 2024
- Tool Calling
- ❌ Not supported
- Vision
- ❌ Not supported
- Audio
- ❌ Not supported
Full Analysis: Microsoft: Phi 4
What is Microsoft: Phi 4?
Microsoft: Phi 4 is an AI model developed by Microsoft, classified as a large language model (LLM). It focuses on text processing and natural language generation. As an open source model, it is available for download, customization, and on-premises deployment. With a context window of 16K tokens, it is suitable for processing short documents and direct prompts.
Pricing & Costs in 2026
Microsoft: Phi 4 is usage-based, priced at $0.125/1M input tokens and $0.5/1M output tokens. For context: 1 million tokens is approximately 750,000 words, or about 10 average-length books. At this aggressive price point, it is one of the most cost-effective options on the market, ideal for high-volume applications like chatbots, bulk document analysis, and automation.
Benchmarks & Performance
Microsoft: Phi 4 was evaluated on 16 different benchmarks, covering categories like Agentic, Coding, Knowledge, Long Context, Math, overall, Reasoning, Tool Use. Results show solid performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Recommended Use Cases
Microsoft: Phi 4 is suitable for a wide range of AI applications: high-volume chatbots and automated support, text generation, summarization, translation, and general assistance.
Comparison with Alternatives
In the 2026 AI model ecosystem, Microsoft: Phi 4 competes directly with similarly capable models. Microsoft competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Frequently Asked Questions
What is Microsoft: Phi 4?
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
How much does Microsoft: Phi 4 cost?
Microsoft: Phi 4 costs $0.125/1M input tokens and $0.5/1M output tokens. For heavy usage (e.g., a chatbot handling 100k messages/month), costs can range from $10 to $1,000 depending on volume.
How does Microsoft: Phi 4 compare with other models?
In available benchmarks, Microsoft: Phi 4 scored: Terminal-Bench Hard: 4/100, SciCode: 26/100, LiveCodeBench: 23/100. See the full table above for a detailed comparison.
Is Microsoft: Phi 4 open source?
Yes, Microsoft: Phi 4 is an open source model. You can deploy it on-premises, customize it via fine-tuning, and maintain full control over your data. Check the official repository for the specific license.
What is Microsoft: Phi 4 best for?
Microsoft: Phi 4 excels at general-purpose language tasks.
Last updated: June 01, 2026 • View methodology →