Model comparison

Gemma 3 4B vs GPT-5.1-Codex

GPT-5.1-Codex is the stronger model overall, scoring 38.6 to 28.1 on the Noometry Index. Gemma 3 4B costs 69× less per token, which makes it the better buy when GPT-5.1-Codex's lead doesn't matter for your workload.

Last verified October 10, 2026. 0 shared benchmarks.

Gemma 3 4B

Google

28.1

Rank #326 Confirmed

GPT-5.1-Codex OpenAI

38.6

Rank #186 Reported

Summary

The widest gap is in agentic & tool use, where GPT-5.1-Codex leads 38.0 to 20.9.
Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $1.25 / $10 for GPT-5.1-Codex.
GPT-5.1-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-5.1-Codex specifications
	Gemma 3 4B	GPT-5.1-Codex
Provider	Google	OpenAI
Noometry Index	28.1	38.6
Released	2025-03-12	2025-11-12
Weights	Open	Proprietary
Context window	131K	400K
Max output	4K	128K
Input $ / M tokens	$0.04	$1.25
Output $ / M tokens	$0.08	$10
Results tracked	22	6

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

Category by category

Coding GPT-5.1-Codex leads

Gemma 3 4B: 35.9 (#215), GPT-5.1-Codex: 41.9 (#116)

Coding benchmarks
Benchmark	Gemma 3 4B	GPT-5.1-Codex
SWE-bench Verified (bash only)	—	66%
LMArena WebDev	—	1337
LMArena Coding	1230	—
ALE-Bench	—	1,245

Agentic & Tool Use GPT-5.1-Codex leads

Gemma 3 4B: 20.9 (#142), GPT-5.1-Codex: 38.0 (#33)

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 4B	GPT-5.1-Codex
Terminal-Bench	—	60.4%
Berkeley Function Calling Leaderboard	19.6%	—
METR Time Horizons	—	70.8%

Reasoning Not comparable

Gemma 3 4B: 13.2 (#335), GPT-5.1-Codex: —

Reasoning benchmarks
Benchmark	Gemma 3 4B	GPT-5.1-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 GPT-5.1-Codex leads

Gemma 3 4B: 16.8 (#292), GPT-5.1-Codex: 30.3 (#235)

Math benchmarks
Benchmark	Gemma 3 4B	GPT-5.1-Codex
OTIS Mock AIME 2024-2025	7.5%	—
ProofBench	—	9%
LMArena Math	1239	—

Knowledge Not comparable

Gemma 3 4B: 11.8 (#299), GPT-5.1-Codex: —

Knowledge benchmarks
Benchmark	Gemma 3 4B	GPT-5.1-Codex
GPQA Diamond	23.2%	—
Vectara Hallucination Rate	6.4%	—
LMArena Expert	1223	—

Multilingual Not comparable

Gemma 3 4B: 42.5 (#194), GPT-5.1-Codex: —

Multilingual benchmarks
Benchmark	Gemma 3 4B	GPT-5.1-Codex
LMArena Non-English	1273	—
LMArena German	1281	—
LMArena Russian	1294	—

Instruction Following Not comparable

Gemma 3 4B: 65.2 (#225), GPT-5.1-Codex: —

Instruction Following benchmarks
Benchmark	Gemma 3 4B	GPT-5.1-Codex
LMArena Instruction Following	1239	—

Long Context Not comparable

Gemma 3 4B: 38.7 (#194), GPT-5.1-Codex: —

Long Context benchmarks
Benchmark	Gemma 3 4B	GPT-5.1-Codex
LMArena Longer Query	1273	—

Writing & Preference Not comparable

Gemma 3 4B: 42.0 (#239), GPT-5.1-Codex: —

Writing & Preference benchmarks
Benchmark	Gemma 3 4B	GPT-5.1-Codex
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 GPT-5.1-Codex?

Which is cheaper, Gemma 3 4B or GPT-5.1-Codex?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GPT-5.1-Codex lists at $1.25 and $10.

Is Gemma 3 4B or GPT-5.1-Codex better for coding?

GPT-5.1-Codex scores higher on coding benchmarks: 41.9 versus 35.9 in the Noometry coding category.

Which has the bigger context window?

GPT-5.1-Codex does, with 400K tokens against 131K.

How many benchmarks do Gemma 3 4B and GPT-5.1-Codex share?

0 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and GPT-5.1-Codex has 6.