Phi-4 Mini Reasoning
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
Advancing the state-of-the-art in AI and computing.
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
Benchmark peer barsfor Long context
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(3)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| AIME 2024 | 57.5 | From official Microsoft technical report, Table 3 (accuracy) | https://arxiv.org/html/2504.21233 |
| MATH-500 | 94.6 | From official Microsoft technical report (accuracy) | https://arxiv.org/html/2504.21233 |
| Google-Proof Q&A | 52.0 | GPQA 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.
Advancing the state-of-the-art in AI and computing.
No tracked provider token pricing is available yet.