LLM Reference

Phi-4 Mini Reasoning

Released
2026-05-16
Last refreshed
2026-05-22
Status
Researched 39d ago
Open sourceCommercial use: permittedLong context

Phi-4 Mini Reasoning is a released long context model with open-source and 128k context; evaluate it while provider pricing coverage matures.

Use it for

  • Teams evaluating long context
  • Workloads that can use a 128k context window

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Family
Phi-4
Released
2026-05-16
Context
128k
Parameters
3.8B
Knowledge cutoff
2025-02
Specialization
reasoning
Openness
Open source
License
MITOSI-approvedCommercial use: permitted
Created by

Advancing the state-of-the-art in AI and computing.

Redmond, Washington, United States
Founded 1991
Website
Pricing

No tracked provider token pricing is available yet.

About

Microsoft Phi-4 Mini with reasoning capabilities optimized for step-by-step problem solving. Distinct from phi-4-mini-flash-reasoning (which emphasizes speed). Engineer note: check if same as phi-4-mini-flash-reasoning in seed; may be a different checkpoint.

Phi-4 Mini Reasoning is an open-source model in the Phi-4 family. The structured metadata tracks a 128k-token context window and reasoning. Headline tracked benchmarks include AIME 2024 57.5, MATH-500 94.6, and Google-Proof Q&A 52.0.

Top use-case fit

Long context

Included by capability and metadata signals in the decision map.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

Reasoning

Benchmark peer barsfor Long context

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(3)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
AIME 202457.5From official Microsoft technical report, Table 3 (accuracy)https://arxiv.org/html/2504.21233
MATH-50094.6From official Microsoft technical report (accuracy)https://arxiv.org/html/2504.21233
Google-Proof Q&A52.0GPQA Diamond (accuracy)https://arxiv.org/html/2504.21233

Migration checks

No linked migration route is available for this model yet.

Compare Phi-4 Mini Reasoning with other models

Frequently asked questions

What is the context window of Phi-4 Mini Reasoning?

Phi-4 Mini Reasoning has a context window of 128k tokens.

When was Phi-4 Mini Reasoning released?

Phi-4 Mini Reasoning was released on 2026-05-16.

What benchmarks has Phi-4 Mini Reasoning been tested on?

Phi-4 Mini Reasoning has been evaluated on 3 benchmarks, including AIME 2024, MATH-500, Google-Proof Q&A.