LLMOpen weights

Phi 4 Reasoning

Microsoft

Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type: LLM
Access: Open weights
Released: April 30, 2025
License: MIT
Parameters: 14000000000
Knowledge cutoff: March 1, 2025

Benchmarks

Reasoning

65.8

Coding

HumanEval	92.9
LiveCodeBench	53.8

Math

AIME 2024	75.3
AIME 2025	62.9

General

IFEval	83.4
MMLU-Pro	74.3
Arena Hard	73.3

Compare Phi 4 Reasoning with

vs Sonar Reasoning Pro vs R1 1776 vs Qwen3.7 Max vs Gemini 3.5 Flash

See all Phi 4 Reasoning alternatives →