Phi-4
Available
2024-12-12
32,000 tokens
Other 开发的 AI 模型，适合多种 AI 应用场景。
Supported modalities:TextCode
Quick Overview
Text Generation1/10
Code Generation1/10
Reasoning2/10
Multimodal1/10
Benchmark Results
Scores from leading benchmark suites.
13.2%
artificial-analysis-intelligence
11.2%
artificial-analysis-coding
18.0%
artificial-analysis-math
Performance Metrics
Latency and throughput performance.
1000ms
P50 Latency
9.467
tokens/sec
Dive Deeper
Explore detailed analyses by topic.
Pricing Info
Feature support
Streaming
Tool calling
JSON mode