Model comparison

Gemma 3 4B vs GPT-5.2 Codex

GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 27.9 on the Noometry Index. Gemma 3 4B costs 96× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.

Last verified October 10, 2026. 0 shared benchmarks.

Gemma 3 4B

Google

27.9

Rank #320 Confirmed

GPT-5.2 Codex OpenAI

42.2

Rank #107 Reported

Summary

The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 40.7 to 20.7.
Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
GPT-5.2 Codex accepts more context: 400K tokens versus 131K.
Gemma 3 4B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 4B and GPT-5.2 Codex specifications
	Gemma 3 4B	GPT-5.2 Codex
Provider	Google	OpenAI
Noometry Index	27.9	42.2
Released	2025-03-12	2025-12-18
Weights	Open	Proprietary
Context window	131K	400K
Max output	4K	128K
Input $ / M tokens	$0.04	$1.75
Output $ / M tokens	$0.08	$14
Results tracked	22	5

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

Category by category

Coding GPT-5.2 Codex leads

Gemma 3 4B: 35.3 (#214), GPT-5.2 Codex: 45.4 (#66)

Coding benchmarks
Benchmark	Gemma 3 4B	GPT-5.2 Codex
SWE-bench Verified (bash only)	—	72.8%
LMArena WebDev	—	1339
SWE-bench Multilingual	—	66.3%
LMArena Coding	1230	—
ALE-Bench	—	1,300

Agentic & Tool Use GPT-5.2 Codex leads

Gemma 3 4B: 20.7 (#134), GPT-5.2 Codex: 40.7 (#20)

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 4B	GPT-5.2 Codex
Terminal-Bench	—	66.5%
Berkeley Function Calling Leaderboard	19.6%	—

Reasoning Not comparable

Gemma 3 4B: 12.7 (#330), GPT-5.2 Codex: —

Reasoning benchmarks
Benchmark	Gemma 3 4B	GPT-5.2 Codex
Kagi LLM Benchmark	25.2%	—
Chess Puzzles	0%	—
LMArena Hard Prompts	1253	—
DTBench	50.9%	—
LMCA	2.8%	—
Epoch Capabilities Index	116.02	—

Math Not comparable

Gemma 3 4B: 15.8 (#286), GPT-5.2 Codex: —

Math benchmarks
Benchmark	Gemma 3 4B	GPT-5.2 Codex
OTIS Mock AIME 2024-2025	7.5%	—
LMArena Math	1239	—

Knowledge Not comparable

Gemma 3 4B: 11.8 (#294), GPT-5.2 Codex: —

Knowledge benchmarks
Benchmark	Gemma 3 4B	GPT-5.2 Codex
GPQA Diamond	23.2%	—
Vectara Hallucination Rate	6.4%	—
LMArena Expert	1223	—

Multilingual Not comparable

Gemma 3 4B: 42.7 (#189), GPT-5.2 Codex: —

Multilingual benchmarks
Benchmark	Gemma 3 4B	GPT-5.2 Codex
LMArena Non-English	1273	—
LMArena German	1281	—
LMArena Russian	1294	—

Instruction Following Not comparable

Gemma 3 4B: 65.4 (#219), GPT-5.2 Codex: —

Instruction Following benchmarks
Benchmark	Gemma 3 4B	GPT-5.2 Codex
LMArena Instruction Following	1239	—

Long Context Not comparable

Gemma 3 4B: 38.6 (#189), GPT-5.2 Codex: —

Long Context benchmarks
Benchmark	Gemma 3 4B	GPT-5.2 Codex
LMArena Longer Query	1274	—

Writing & Preference Not comparable

Gemma 3 4B: 42.2 (#234), GPT-5.2 Codex: —

Writing & Preference benchmarks
Benchmark	Gemma 3 4B	GPT-5.2 Codex
LMArena Text	1291	—
LMArena Creative Writing	1270	—
EQ-Bench Creative Writing	1068	—
LMArena Multi-Turn	1255	—

Frequently asked questions

Is Gemma 3 4B better than GPT-5.2 Codex?

Which is cheaper, Gemma 3 4B or GPT-5.2 Codex?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.

Is Gemma 3 4B or GPT-5.2 Codex better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 35.3 in the Noometry coding category.

Which has the bigger context window?

GPT-5.2 Codex does, with 400K tokens against 131K.

How many benchmarks do Gemma 3 4B and GPT-5.2 Codex share?

0 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and GPT-5.2 Codex has 5.