Model comparison

Gemma 3 4B vs Phi-4 Mini

Phi-4 Mini is the stronger model overall, scoring 30.9 to 28.1 on the Noometry Index. Gemma 3 4B costs 2.6× less per token, which makes it the better buy when Phi-4 Mini's lead doesn't matter for your workload.

Last verified October 10, 2026. 1 shared benchmarks.

Gemma 3 4B

Google

28.1

Rank #326 Confirmed

Phi-4 Mini

Microsoft

30.9

Rank #283 Reported

Summary

They share 1 benchmark with published results for both. Gemma 3 4B scores higher in 1 category and Phi-4 Mini in 2 categories; 3 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Phi-4 Mini leads 25.3 to 11.8.
The biggest single-benchmark swing is Vectara Hallucination Rate: 6.4% for Gemma 3 4B and 23.5% for Phi-4 Mini.
Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.075 / $0.30 for Phi-4 Mini.
Gemma 3 4B accepts more context: 131K tokens versus 128K.

Side by side

Gemma 3 4B and Phi-4 Mini specifications
	Gemma 3 4B	Phi-4 Mini
Provider	Google	Microsoft
Noometry Index	28.1	30.9
Released	2025-03-12	2024-12-11
Weights	Open	Open
Context window	131K	128K
Max output	4K	4K
Input $ / M tokens	$0.04	$0.075
Output $ / M tokens	$0.08	$0.30
Results tracked	22	3

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

Category by category

Coding Gemma 3 4B leads

Gemma 3 4B: 35.9 (#215), Phi-4 Mini: 28.1 (#317)

Coding benchmarks
Benchmark	Gemma 3 4B	Phi-4 Mini
SciCode	—	10.8%
LMArena Coding	1230	—

Agentic & Tool Use Not comparable

Gemma 3 4B: 20.9 (#142), Phi-4 Mini: —

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 4B	Phi-4 Mini
Berkeley Function Calling Leaderboard	19.6%	—

Reasoning Phi-4 Mini leads

Gemma 3 4B: 13.2 (#335), Phi-4 Mini: 22.4 (#195)

Reasoning benchmarks
Benchmark	Gemma 3 4B	Phi-4 Mini
Kagi LLM Benchmark	25.2%	—
CritPt	—	0%
Chess Puzzles	0%	—
LMArena Hard Prompts	1253	—
DTBench	50.9%	—
LMCA	2.8%	—
Epoch Capabilities Index	116.02	—

Math Not comparable

Gemma 3 4B: 16.8 (#292), Phi-4 Mini: —

Math benchmarks
Benchmark	Gemma 3 4B	Phi-4 Mini
OTIS Mock AIME 2024-2025	7.5%	—
LMArena Math	1239	—

Knowledge Phi-4 Mini leads

Gemma 3 4B: 11.8 (#299), Phi-4 Mini: 25.3 (#262)

Knowledge benchmarks
Benchmark	Gemma 3 4B	Phi-4 Mini
Vectara Hallucination Rate	6.4%	23.5%
GPQA Diamond	23.2%	—
LMArena Expert	1223	—

Multilingual Not comparable

Gemma 3 4B: 42.5 (#194), Phi-4 Mini: —

Multilingual benchmarks
Benchmark	Gemma 3 4B	Phi-4 Mini
LMArena Non-English	1273	—
LMArena German	1281	—
LMArena Russian	1294	—

Instruction Following Not comparable

Gemma 3 4B: 65.2 (#225), Phi-4 Mini: —

Instruction Following benchmarks
Benchmark	Gemma 3 4B	Phi-4 Mini
LMArena Instruction Following	1239	—

Long Context Not comparable

Gemma 3 4B: 38.7 (#194), Phi-4 Mini: —

Long Context benchmarks
Benchmark	Gemma 3 4B	Phi-4 Mini
LMArena Longer Query	1273	—

Writing & Preference Not comparable

Gemma 3 4B: 42.0 (#239), Phi-4 Mini: —

Writing & Preference benchmarks
Benchmark	Gemma 3 4B	Phi-4 Mini
LMArena Text	1291	—
LMArena Creative Writing	1271	—
EQ-Bench Creative Writing	1068	—
LMArena Multi-Turn	1255	—

Frequently asked questions

Is Gemma 3 4B better than Phi-4 Mini?

Which is cheaper, Gemma 3 4B or Phi-4 Mini?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Phi-4 Mini lists at $0.075 and $0.30.

Is Gemma 3 4B or Phi-4 Mini better for coding?

Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 28.1 in the Noometry coding category.

Which has the bigger context window?

Gemma 3 4B does, with 131K tokens against 128K.

How many benchmarks do Gemma 3 4B and Phi-4 Mini share?

1 benchmark has published results for both models. Gemma 3 4B has 22 scored results on Noometry and Phi-4 Mini has 3.