Compare / Phi-4-reasoning-plus vs Phi-4

Phi-4-reasoning-plus vs Phi-4

Updated November 2026

Verdict

Phi-4-reasoning-plus scores higher on the Small LM Index: 54.4 vs 44.7, although their likely ranges overlap, so the lead is not certain. On the 2 benchmarks both labs report, Phi-4-reasoning-plus wins 2 and Phi-4 wins 0. Both need about 11.4 GB of memory at 4-bit quantization. Only Phi-4 has a hosted API on OpenRouter ($0.070 per million tokens); the other has to be self-hosted.

Pick Phi-4-reasoning-plus if…

you want the strongest model overall
you work with long documents

Pick Phi-4 if…

you want a hosted API rather than running it yourself
you want the more widely used model (more quantized builds and community support)

Specifications

	Phi-4-reasoning-plus	Phi-4
Small LM Index	54.4 (likely 50–59)	44.7 (likely 35–55)
Lab	Microsoft (Phi) · United States	Microsoft (Phi) · United States
Released	2025-04-30	2024-12-12
Parameters	14.7B (dense)	14.7B (dense)
Memory at 4-bit	~11.4 GB	~11.4 GB
Context window	32K tokens	16K tokens
Input	text	text
Reasoning	Always thinks	No thinking
License	MIT	MIT
API price / 1M tokens	Self-host only	$0.070 ($0.056 in, $0.11 out)
Hugging Face downloads (30 days)	4.9K	327K

Benchmarks

Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.

Benchmark	Phi-4-reasoning-plus	Phi-4
MMLU-Pro Knowledge	76.0	70.4
GPQA Diamond Knowledge	69.3	56.1
AIME Math	78.0	≈ 61
LiveCodeBench Coding	53.1	≈ 50

Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.

Questions

Which is better, Phi-4-reasoning-plus or Phi-4?

Which is cheaper to run?

Only Phi-4 has a hosted API on OpenRouter ($0.070 per million tokens); the other has to be self-hosted. Both need about 11.4 GB of memory at 4-bit quantization.

Which has the longer context window?

Phi-4-reasoning-plus has the longer context window: 32K tokens against 16K.

Can I use Phi-4-reasoning-plus and Phi-4 commercially?

Both are released under the MIT license. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.