Microsoft model product
Phi 4 Reasoning Plus
Phi-4-reasoning-plus is a state-of-the-art open-weight reasoning model finetuned from Phi-4 using supervised fine-tuning and reinforcement learning.
Updated Aug 17, 2026. Default version: Phi 4 Reasoning Plus
LLMBoard Score26.0Phi 4 Reasoning Plus
Coverage100%9 benchmark families
Context windowN/ATokens
Official input price$0.125Azure API
Phi 4 Reasoning Plus Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Phi 4 Reasoning Plus Benchmark Results
Benchmark scores for Phi 4 Reasoning Plus.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkFlenQA | Score97.9% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkOmniMath | Score81.9% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkPhiBench | Score74.2% | Rank01 | Participants3 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkHumanEval+ | Score92.3% | Rank02 | Participants10 | Percentile88.9% | EvidenceC | Evaluated |
| BenchmarkArena Hard | Score79.0% | Rank07 | Participants26 | Percentile76.0% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score81.3% | Rank24 | Participants53 | Percentile55.8% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score84.9% | Rank38 | Participants67 | Percentile43.9% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score53.1% | Rank44 | Participants75 | Percentile41.9% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score76.0% | Rank72 | Participants134 | Percentile46.6% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score78.0% | Rank76 | Participants115 | Percentile34.2% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score68.9% | Rank139 | Participants239 | Percentile42.0% | EvidenceC | Evaluated |
Phi 4 Reasoning Plus Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Phi 4 Reasoning Plus Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.125 input, $0.50 output per 1M
- Official provider
- Azure
- Lowest third-party
- From $0.125 input, $0.50 output per 1M via Azure Cognitive Services
- Tracked offerings
- 2
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAzure Cognitive Services | Provider model IDphi-4-reasoning-plus | Regionglobal | Input / 1M$0.125 | Output / 1M$0.50 | Context32K | Updated |
| ProviderAzure | Provider model IDphi-4-reasoning-plus | Regionglobal | Input / 1M$0.125 | Output / 1M$0.50 | Context32K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Phi 4 Reasoning Plus Runtime Performance
Provider-specific output speed and catalog latency for Phi 4 Reasoning Plus. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Phi 4 Reasoning Plus Specifications
Technical details for the model's default version.
- Version
- Phi 4 Reasoning Plus
- Released
- Apr 30, 2025
- Knowledge cutoff
- Mar 1, 2025
- Parameters
- 14B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- MIT
Phi 4 Reasoning Plus Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionPhi 4 Reasoning Plus | Released | LLMBoard26.0 | Parameters14B | ContextN/A | Max outputN/A | Open weightsNo | LicenseMIT |
Phi 4 Reasoning Plus vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Phi 4 Reasoning Plus
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MI
Phi 4 Reasoning
Microsoft
MI
Phi 4 Mini Reasoning
Microsoft
MI
Phi 4
Microsoft
MI
Phi 4 multimodal
Microsoft
MI
MAI Code 1.1 Flash
Microsoft
MI
Phi 3.5 MoE
Microsoft
What is Phi 4 Reasoning Plus?
Key information about Phi 4 Reasoning Plus and its available data.
Phi-4-reasoning-plus is a state-of-the-art open-weight reasoning model finetuned from Phi-4 using supervised fine-tuning and reinforcement learning. It focuses on math, science, and coding skills. This 'plus' version has higher accuracy due to additional RL training but may have higher latency.
Data as of 2026-08-17.
FAQ
Common questions about Phi 4 Reasoning Plus.
When was Phi 4 Reasoning Plus released?
Phi 4 Reasoning Plus's default version was released on Apr 30, 2025.
How much does Phi 4 Reasoning Plus cost?
Phi 4 Reasoning Plus's official API price is $0.125 per million input tokens and $0.50 per million output tokens via Azure. The lowest tracked third-party offer starts at $0.125 input and $0.50 output via Azure Cognitive Services.
Who created Phi 4 Reasoning Plus?
Phi 4 Reasoning Plus was created by Microsoft.
What is the context window for Phi 4 Reasoning Plus?
A context window is not available for the default version.
Is Phi 4 Reasoning Plus open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Phi 4 Reasoning Plus?
2 provider offerings are linked to the default version.
What models should I compare Phi 4 Reasoning Plus with?
Nearby ranked alternatives include Qwen3 VL 30B A3B, Qwen3 VL 8B Thinking, Gemini 2.0 Flash.