What is Phi-4-mini-flash-reasoning?

Phi-4-mini-flash-reasoning is a large language model from Microsoft, released on July 9, 2025. It accepts text input.

When was Phi-4-mini-flash-reasoning released?

Microsoft released Phi-4-mini-flash-reasoning on July 9, 2025.

What is Phi-4-mini-flash-reasoning's context window?

Phi-4-mini-flash-reasoning has a 64K-token context window.

How does Phi-4-mini-flash-reasoning score on benchmarks?

Phi-4-mini-flash-reasoning has 4 cited benchmark scores, including AIME24 52.29%, AIME25 33.59% and GPQA Diamond 45.08%. Each score links to its source.

Phi-4-mini-flash-reasoning

Microsoft·Pending·Released 2025-07-09text

Context64k

Max output-

Input / 1M-

Output / 1M-

Cached in-

Benchmarks4

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

AIME24

#2/252.29% ↗

AIME25

#12/1233.59% ↗

GPQA Diamond

#81/8345.08% ↗

Math500

92.45% ↗

Compare

vs Gemini 4 Argon vs GPT-6.1 Sol vs Claude Sonnet 5.5 vs Muse Spark 1.3 vs GPT-6 Sol vs GPT-6 Luna vs Claude Opus 5.5 vs GPT-6 Astra

More from Microsoft

MAI-Thinking-1 Phi-4 Phi-4 Reasoning Phi-4 Mini Reasoning Phi-4 Multimodal Instruct Phi-4-Reasoning-Vision-15B

Phi-4-mini-flash-reasoning FAQ

What is Phi-4-mini-flash-reasoning?: Phi-4-mini-flash-reasoning is a large language model from Microsoft, released on July 9, 2025. It accepts text input.
When was Phi-4-mini-flash-reasoning released?: Microsoft released Phi-4-mini-flash-reasoning on July 9, 2025.
What is Phi-4-mini-flash-reasoning's context window?: Phi-4-mini-flash-reasoning has a 64K-token context window.
How does Phi-4-mini-flash-reasoning score on benchmarks?: Phi-4-mini-flash-reasoning has 4 cited benchmark scores, including AIME24 52.29%, AIME25 33.59% and GPQA Diamond 45.08%. Each score links to its source.

Access Phi-4-mini-flash-reasoning and every other model through one endpoint with automatic failover: Respan gateway.