Model comparison

MiMo-V2.6-Pro vs Phi-4 Mini

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 30.9 on the Noometry Index. Phi-4 Mini costs 4.1× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.

Last verified October 10, 2026. 2 shared benchmarks.

MiMo-V2.6-Pro Xiaomi

50.3

Rank #49 Confirmed

Phi-4 Mini

Microsoft

30.9

Rank #283 Reported

Summary

They share 2 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 3 categories and Phi-4 Mini in 0 categories; 3 gaps are clear of the uncertainty.
The widest gap is in coding, where MiMo-V2.6-Pro leads 55.5 to 28.1.
The biggest single-benchmark swing is SciCode: 60.9% for MiMo-V2.6-Pro and 10.8% for Phi-4 Mini.
Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 128K.

Side by side

MiMo-V2.6-Pro and Phi-4 Mini specifications
	MiMo-V2.6-Pro	Phi-4 Mini
Provider	Xiaomi	Microsoft
Noometry Index	50.3	30.9
Released	2026-09-21	2024-12-11
Weights	Open	Open
Context window	1.05M	128K
Max output	131K	4K
Input $ / M tokens	$0.43	$0.075
Output $ / M tokens	$0.87	$0.30
Results tracked	19	3

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 55.5 (#23), Phi-4 Mini: 28.1 (#317)

Coding benchmarks
Benchmark	MiMo-V2.6-Pro	Phi-4 Mini
SciCode	60.9%	10.8%
LMArena WebDev	1629	—
LMArena Coding	1534	—
ALE-Bench	1,158	—

Agentic & Tool Use Not comparable

MiMo-V2.6-Pro: 37.5 (#35), Phi-4 Mini: —

Agentic & Tool Use benchmarks
Benchmark	MiMo-V2.6-Pro	Phi-4 Mini
APEX-Agents	59.5%	—

Reasoning MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 43.1 (#50), Phi-4 Mini: 22.4 (#195)

Reasoning benchmarks
Benchmark	MiMo-V2.6-Pro	Phi-4 Mini
CritPt	26.6%	0%
LMArena Hard Prompts	1512	—

Math Not comparable

MiMo-V2.6-Pro: 54.5 (#45), Phi-4 Mini: —

Math benchmarks
Benchmark	MiMo-V2.6-Pro	Phi-4 Mini
ProofBench	70%	—
LMArena Math	1494	—

Knowledge MiMo-V2.6-Pro leads

MiMo-V2.6-Pro: 43.5 (#92), Phi-4 Mini: 25.3 (#262)

Knowledge benchmarks
Benchmark	MiMo-V2.6-Pro	Phi-4 Mini
Vectara Hallucination Rate	—	23.5%
LMArena Expert	1543	—

Multimodal Not comparable

MiMo-V2.6-Pro: 40.8 (#43), Phi-4 Mini: —

Multimodal benchmarks
Benchmark	MiMo-V2.6-Pro	Phi-4 Mini
LMArena Vision	1264	—

Multilingual Not comparable

MiMo-V2.6-Pro: 56.9 (#14), Phi-4 Mini: —

Multilingual benchmarks
Benchmark	MiMo-V2.6-Pro	Phi-4 Mini
LMArena Non-English	1474	—
LMArena Chinese	1529	—
LMArena Russian	1480	—

Instruction Following Not comparable

MiMo-V2.6-Pro: 78.2 (#12), Phi-4 Mini: —

Instruction Following benchmarks
Benchmark	MiMo-V2.6-Pro	Phi-4 Mini
LMArena Instruction Following	1493	—

Long Context Not comparable

MiMo-V2.6-Pro: 46.0 (#27), Phi-4 Mini: —

Long Context benchmarks
Benchmark	MiMo-V2.6-Pro	Phi-4 Mini
LMArena Longer Query	1501	—

Writing & Preference Not comparable

MiMo-V2.6-Pro: 66.8 (#33), Phi-4 Mini: —

Writing & Preference benchmarks
Benchmark	MiMo-V2.6-Pro	Phi-4 Mini
LMArena Text	1492	—
LMArena Creative Writing	1468	—
LMArena Multi-Turn	1464	—

Frequently asked questions

Is MiMo-V2.6-Pro better than Phi-4 Mini?

Which is cheaper, MiMo-V2.6-Pro or Phi-4 Mini?

Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.

Is MiMo-V2.6-Pro or Phi-4 Mini better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 28.1 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2.6-Pro does, with 1.05M tokens against 128K.

How many benchmarks do MiMo-V2.6-Pro and Phi-4 Mini share?

2 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Phi-4 Mini has 3.