Models

Phi-4 Mini Instruct

MicrosoftMicrosoftUnited States

Phi-4 Mini is a lightweight, efficient small language model from Microsoft's Phi series, optimized for high performance on resource-constrained devices. It excels at instruction following, reasoning, and code generation tasks while maintaining a small footprint.

FastCheapReasoningCoding
Input / 1M tokens
$0.00
Output / 1M tokens
$0.00
Output tokens/s
44.19
First-token seconds
0.34s
Supported plans
0

Benchmark history

Evaluations

15

TAU2

Measured May 14, 2026Source

Score

0.08

Terminalbench Hard

Measured May 14, 2026Source

Score

0

Lcr

Measured May 14, 2026Source

Score

0.14

Ifbench

Measured May 14, 2026Source

Score

0.21

Aime 25

Measured May 14, 2026Source

Score

0.07

Aime

Measured May 14, 2026Source

Score

0.03

Math 500

Measured May 14, 2026Source

Score

0.7

Scicode

Measured May 14, 2026Source

Score

0.11

Livecodebench

Measured May 14, 2026Source

Score

0.13

Hle

Measured May 14, 2026Source

Score

0.04

Gpqa

Measured May 14, 2026Source

Score

0.33

Mmlu Pro

Measured May 14, 2026Source

Score

0.47

Artificial Analysis Math Index

Measured May 14, 2026Source

Score

6.7

Artificial Analysis Coding Index

Measured May 14, 2026Source

Score

3.6

Artificial Analysis Intelligence Index

Measured May 14, 2026Source

Score

8.4

Plan availability

Products and plans that support this model

0
No products or plans have been linked to this model yet.

Discussion

Thinking... Make sure you are connected to GitHub server