Microsoft
Phi-4-mini
Tool calling
Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks
- Context
- 128K
- Released
- 1y ago
- Parameters
- —
Sources:models.dev
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Microsoft
- Model family
- Phi
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- December 11, 2024
- Model ID
microsoft/phi-4-mini- Openness
- Open weights
- License
- —
- Parameters
- —
- Input modalities
- text
- Output modalities
- text
- Modality
- text->text
- Max output tokens
- 4K
- Knowledge cutoff
- 2023-10
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- microsoft/phi-4-mini
- Source family
- phi
- Last updated
- 2024-12-11
- Knowledge cutoff
- 2023-10
- Model context
- 128K
- Model output limit
- 4K
- Open weights
- Yes
- File attachments
- No
- Reasoning
- No
- Tool calling
- Yes
- Temperature control
- Yes
Downloadable weights
Published benchmarks
| Benchmark | Score | Evaluation details | Evidence |
|---|---|---|---|
| MMLU | 67.3 · accuracy | — | Source |
Complete source record (JSON)
{
"id": "microsoft/phi-4-mini",
"name": "Phi-4-mini",
"description": "Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks",
"family": "phi",
"last_updated": "2024-12-11",
"knowledge": "2023-10",
"attachment": false,
"reasoning": false,
"tool_call": true,
"temperature": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"benchmarks": [
{
"name": "MMLU",
"score": 67.3,
"source": "https://huggingface.co/microsoft/Phi-4-mini-instruct/resolve/main/README.md",
"metric": "accuracy"
}
],
"release_date": "2024-12-11",
"open_weights": true,
"links": [
{
"url": "https://huggingface.co/microsoft/Phi-4-mini-instruct",
"label": "Weights",
"type": "weights"
}
]
}Infrastructure
Provider availability
Provider endpoint data will appear after this model's first OpenRouter endpoint sync.
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.