Microsoft
Phi-4
Phi-4 is a Microsoft language-model profile in the Easy Benchmarks snapshot. Use this page to compare its measured Artificial Analysis scores, output speed, time to first token, pricing, and relative ranking against other models in the local catalog.
Azure AI Foundry modelsOperational Metrics
Output Speed41.6 tok/s
First Token0.51s
Blended Price$0.219/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseDec 12, 2024
Context Windown/a
Modalitiesn/a
Strength: TTFT
Rank #48 across 293 models.
0.51s
Strength: Input $
Rank #56 across 325 models.
$0.125/M
Strength: Blended $
Rank #61 across 325 models.
$0.219/M
Watch Area: Speed
Rank #250 across 293 models.
41.6 tok/s
Watch Area: HLE
Rank #402 across 474 models.
4.1%
Watch Area: Overall
Rank #412 across 500 models.
10.4
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 10.4 | #412 |
| Artificial Analysis Coding Index | coding | 11.2 | #296 |
| Artificial Analysis Math Index | math | 18.0 | #214 |
| MMLU-Pro | reasoning | 71.4% | #210 |