Microsoft
Phi-4
Quality Score8.3
Value Score7.3
Reliability22.1
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 16k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.125
- Output
- $0.500
- Cached Input
- not available
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 4.6
- Coding
- not available
- Agentic
- not available
- Omniscience
- -55.7
- Correct
- 14.1%
- Blended price
- $0.163
Answer outcomes
Correct 14.1%Incorrect 69.8%Abstained 16.2%
Artificial Analysis benchmarks
- SciCode
- 26%
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 57%
- CritPt
- 0%
- AA-Omniscience
- 22%
- AA-LCR
- 0%
Similar models
- Phi-4 Mini InstructMicrosoftQuality Score 6.4Value Score 8.2
- Phi-4 Multimodal InstructMicrosoftQuality Score not availableValue Score not available
- Granite 4.0 H SmallIBMQuality Score 8.0Value Score 8.0
- Nova MicroAmazonQuality Score 7.3Value Score 7.0
- Olmo 3.1 32B InstructAllen Institute for AIQuality Score 8.6Value Score not available
- Qwen3 Omni 30B A3B InstructAlibabaQuality Score 7.1Value Score 6.8