Phi-4-reasoning

Phi-4-reasoning

Microsoft
+
+

Related Products

  • Ango Hub
    15 Ratings
    Visit Website
  • Buildium
    2,458 Ratings
    Visit Website
  • TrustInSoft Analyzer
    6 Ratings
    Visit Website
  • RetailEdge
    199 Ratings
    Visit Website
  • Pipedrive
    9,703 Ratings
    Visit Website
  • AthenaHQ
    30 Ratings
    Visit Website
  • Evertune
    1 Rating
    Visit Website
  • ONLYOFFICE Docs
    708 Ratings
    Visit Website
  • RaimaDB
    10 Ratings
    Visit Website
  • JOpt.TourOptimizer
    10 Ratings
    Visit Website

About

Phi-4-reasoning is a 14-billion parameter transformer-based language model optimized for complex reasoning tasks, including math, coding, algorithmic problem solving, and planning. Trained via supervised fine-tuning of Phi-4 on carefully curated "teachable" prompts and reasoning demonstrations generated using o3-mini, it generates detailed reasoning chains that effectively leverage inference-time compute. Phi-4-reasoning incorporates outcome-based reinforcement learning to produce longer reasoning traces. It outperforms significantly larger open-weight models such as DeepSeek-R1-Distill-Llama-70B and approaches the performance levels of the full DeepSeek-R1 model across a wide range of reasoning tasks. Phi-4-reasoning is designed for environments with constrained computing or latency. Fine-tuned with synthetic data generated by DeepSeek-R1, it provides high-quality, step-by-step problem solving.

About

Step 3.5 Flash is an advanced open source foundation language model engineered for frontier reasoning and agentic capabilities with exceptional efficiency, built on a sparse Mixture of Experts (MoE) architecture that selectively activates only about 11 billion of its ~196 billion parameters per token to deliver high-density intelligence and real-time responsiveness. Its 3-way Multi-Token Prediction (MTP-3) enables generation throughput in the hundreds of tokens per second for complex multi-step reasoning chains and task execution, and it supports efficient long contexts with a hybrid sliding window attention approach that reduces computational overhead across large datasets or codebases. It demonstrates robust performance on benchmarks for reasoning, coding, and agentic tasks, rivaling or exceeding many larger proprietary models, and includes a scalable reinforcement learning framework for consistent self-improvement.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

Educators and developers seeking an AI tool offering models for complex reasoning tasks

Audience

Developers, researchers, and AI engineers who want a powerful open source foundational AI model capable of fast, deep reasoning, coding assistance, and agentic task execution

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

No information available.
Free Version
Free Trial

Pricing

Free
Free Version
Free Trial

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Microsoft
Founded: 1975
United States
azure.microsoft.com/en-us/blog/one-year-of-phi-small-language-models-making-big-leaps-in-ai/

Company Information

StepFun
Founded: 2023
China
static.stepfun.com/blog/step-3.5-flash/

Alternatives

Alternatives

MiMo-V2-Flash

MiMo-V2-Flash

Xiaomi Technology
GLM-4.5

GLM-4.5

Z.ai
Open R1

Open R1

Open R1
MiniMax M2.5

MiniMax M2.5

MiniMax
DeepSeek R1

DeepSeek R1

DeepSeek
DeepSeek-V2

DeepSeek-V2

DeepSeek
DeepCoder

DeepCoder

Agentica Project

Categories

Categories

Integrations

Hugging Face
GitHub
Microsoft Azure
Microsoft Foundry
Microsoft Foundry Models
ModelScope
arXiv

Integrations

Hugging Face
GitHub
Microsoft Azure
Microsoft Foundry
Microsoft Foundry Models
ModelScope
arXiv
Claim Phi-4-reasoning and update features and information
Claim Phi-4-reasoning and update features and information
Claim Step 3.5 Flash and update features and information
Claim Step 3.5 Flash and update features and information