Model comparison

Gemma 3 4B vs o3-pro

o3-pro is the stronger model overall, scoring 42.9 to 28.1 on the Noometry Index. Gemma 3 4B costs 700× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.

Last verified October 10, 2026. 5 shared benchmarks.

Gemma 3 4B

Google

28.1

Rank #326 Confirmed

o3-pro OpenAI

42.9

Rank #105 Confirmed

Summary

They share 5 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and o3-pro in 5 categories; 5 gaps are clear of the uncertainty.
The widest gap is in long context, where o3-pro leads 72.2 to 38.7.
The biggest single-benchmark swing is Kagi LLM Benchmark: 25.2% for Gemma 3 4B and 72.1% for o3-pro.
Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $20 / $80 for o3-pro.
o3-pro accepts more context: 200K tokens versus 131K.
Gemma 3 4B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 4B and o3-pro specifications
	Gemma 3 4B	o3-pro
Provider	Google	OpenAI
Noometry Index	28.1	42.9
Released	2025-03-12	2025-06-10
Weights	Open	Proprietary
Context window	131K	200K
Max output	4K	100K
Input $ / M tokens	$0.04	$20
Output $ / M tokens	$0.08	$80
Results tracked	22	12

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

Category by category

Coding o3-pro leads

Gemma 3 4B: 35.9 (#215), o3-pro: 55.5 (#24)

Coding benchmarks
Benchmark	Gemma 3 4B	o3-pro
Aider Polyglot	—	84.9%
WeirdML	—	58.2%
LMArena Coding	1230	—

Agentic & Tool Use Not comparable

Gemma 3 4B: 20.9 (#142), o3-pro: —

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 4B	o3-pro
Berkeley Function Calling Leaderboard	19.6%	—

Reasoning o3-pro leads

Gemma 3 4B: 13.2 (#335), o3-pro: 23.8 (#171)

Reasoning benchmarks
Benchmark	Gemma 3 4B	o3-pro
Kagi LLM Benchmark	25.2%	72.1%
DTBench	50.9%	86.9%
LMCA	2.8%	38.5%
Epoch Capabilities Index	116.02	147.42
ARC-AGI-2	—	4.9%
ARC-AGI-1	—	59.3%
Chess Puzzles	0%	—
LMArena Hard Prompts	1253	—

Math Not comparable

Gemma 3 4B: 16.8 (#292), o3-pro: —

Math benchmarks
Benchmark	Gemma 3 4B	o3-pro
OTIS Mock AIME 2024-2025	7.5%	—
LMArena Math	1239	—

Knowledge o3-pro leads

Gemma 3 4B: 11.8 (#299), o3-pro: 29.5 (#238)

Knowledge benchmarks
Benchmark	Gemma 3 4B	o3-pro
Vectara Hallucination Rate	6.4%	23.3%
GPQA Diamond	23.2%	—
Confabulations	—	14.2%
LMArena Expert	1223	—

Multilingual Not comparable

Gemma 3 4B: 42.5 (#194), o3-pro: —

Multilingual benchmarks
Benchmark	Gemma 3 4B	o3-pro
LMArena Non-English	1273	—
LMArena German	1281	—
LMArena Russian	1294	—

Instruction Following Not comparable

Gemma 3 4B: 65.2 (#225), o3-pro: —

Instruction Following benchmarks
Benchmark	Gemma 3 4B	o3-pro
LMArena Instruction Following	1239	—

Long Context o3-pro leads

Gemma 3 4B: 38.7 (#194), o3-pro: 72.2 (#1)

Long Context benchmarks
Benchmark	Gemma 3 4B	o3-pro
Fiction.LiveBench	—	97.2%
LMArena Longer Query	1273	—

Writing & Preference o3-pro leads

Gemma 3 4B: 42.0 (#239), o3-pro: 57.1 (#133)

Writing & Preference benchmarks
Benchmark	Gemma 3 4B	o3-pro
LMArena Text	1291	—
LMArena Creative Writing	1271	—
Short-Story Creative Writing	—	84.4%
EQ-Bench Creative Writing	1068	—
LMArena Multi-Turn	1255	—

Frequently asked questions

Is Gemma 3 4B better than o3-pro?

Which is cheaper, Gemma 3 4B or o3-pro?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; o3-pro lists at $20 and $80.

Is Gemma 3 4B or o3-pro better for coding?

o3-pro scores higher on coding benchmarks: 55.5 versus 35.9 in the Noometry coding category.

Which has the bigger context window?

o3-pro does, with 200K tokens against 131K.

How many benchmarks do Gemma 3 4B and o3-pro share?

5 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and o3-pro has 12.