Model comparison

Gemma 4 26B A4B IT vs GPT-5.3 Codex

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 43.5 on the Noometry Index. Gemma 4 26B A4B IT costs 45× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

Last verified October 10, 2026. 4 shared benchmarks.

Gemma 4 26B A4B IT

Google

43.5

Rank #92 Confirmed

GPT-5.3 Codex OpenAI

45.8

Rank #69 Reported

Summary

They share 4 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 0 categories and GPT-5.3 Codex in 1 category; one gap is clear of the uncertainty.
The widest gap is in coding, where GPT-5.3 Codex leads 48.6 to 39.0.
The biggest single-benchmark swing is WeirdML: 35.2% for Gemma 4 26B A4B IT and 79.3% for GPT-5.3 Codex.
Gemma 4 26B A4B IT is cheaper at $0.0675 / $0.23 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
GPT-5.3 Codex accepts more context: 400K tokens versus 262K.
Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.

Side by side

Gemma 4 26B A4B IT and GPT-5.3 Codex specifications
	Gemma 4 26B A4B IT	GPT-5.3 Codex
Provider	Google	OpenAI
Noometry Index	43.5	45.8
Released	2026-04-02	2026-02-05
Weights	Open	Proprietary
Context window	262K	400K
Max output	33K	128K
Input $ / M tokens	$0.0675	$1.75
Output $ / M tokens	$0.23	$14
Results tracked	28	8

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

Category by category

Coding GPT-5.3 Codex leads

Gemma 4 26B A4B IT: 39.0 (#164), GPT-5.3 Codex: 48.6 (#56)

Coding benchmarks
Benchmark	Gemma 4 26B A4B IT	GPT-5.3 Codex
LMArena WebDev	1359	1409
WeirdML	35.2%	79.3%
ALE-Bench	927.17	1,655
SWE-bench Verified	—	74.8%
SciCode	40%	—
LMArena Coding	1447	—

Agentic & Tool Use Not comparable

Gemma 4 26B A4B IT: —, GPT-5.3 Codex: 48.0 (#9)

Agentic & Tool Use benchmarks
Benchmark	Gemma 4 26B A4B IT	GPT-5.3 Codex
Terminal-Bench	—	78.4%
METR Time Horizons	—	74.5%
Vending-Bench 2	—	5,940

Reasoning Not comparable

Gemma 4 26B A4B IT: 21.8 (#213), GPT-5.3 Codex: —

Reasoning benchmarks
Benchmark	Gemma 4 26B A4B IT	GPT-5.3 Codex
Epoch Capabilities Index	141.85	156.77
CritPt	0%	—
Chess Puzzles	6%	—
LMArena Hard Prompts	1439	—
DTBench	74.9%	—
LMCA	29.7%	—

Math Not comparable

Gemma 4 26B A4B IT: 47.6 (#67), GPT-5.3 Codex: —

Math benchmarks
Benchmark	Gemma 4 26B A4B IT	GPT-5.3 Codex
OTIS Mock AIME 2024-2025	82.2%	—
LMArena Math	1470	—

Knowledge Not comparable

Gemma 4 26B A4B IT: 45.7 (#85), GPT-5.3 Codex: —

Knowledge benchmarks
Benchmark	Gemma 4 26B A4B IT	GPT-5.3 Codex
GPQA Diamond	73.2%	—
Vectara Hallucination Rate	5.2%	—
LMArena Expert	1447	—

Multimodal Not comparable

Gemma 4 26B A4B IT: 40.6 (#46), GPT-5.3 Codex: —

Multimodal benchmarks
Benchmark	Gemma 4 26B A4B IT	GPT-5.3 Codex
LMArena Vision	1260	—

Multilingual Not comparable

Gemma 4 26B A4B IT: 53.1 (#71), GPT-5.3 Codex: —

Multilingual benchmarks
Benchmark	Gemma 4 26B A4B IT	GPT-5.3 Codex
LMArena Non-English	1421	—
LMArena Chinese	1495	—
LMArena French	1460	—
LMArena Russian	1434	—
LMArena Spanish	1417	—

Instruction Following Not comparable

Gemma 4 26B A4B IT: 74.8 (#82), GPT-5.3 Codex: —

Instruction Following benchmarks
Benchmark	Gemma 4 26B A4B IT	GPT-5.3 Codex
LMArena Instruction Following	1420	—

Long Context Not comparable

Gemma 4 26B A4B IT: 43.6 (#91), GPT-5.3 Codex: —

Long Context benchmarks
Benchmark	Gemma 4 26B A4B IT	GPT-5.3 Codex
LMArena Longer Query	1428	—

Writing & Preference Not comparable

Gemma 4 26B A4B IT: 58.6 (#115), GPT-5.3 Codex: —

Writing & Preference benchmarks
Benchmark	Gemma 4 26B A4B IT	GPT-5.3 Codex
LMArena Text	1434	—
LMArena Creative Writing	1402	—
EQ-Bench Creative Writing	1305	—
LMArena Multi-Turn	1441	—

Frequently asked questions

Is Gemma 4 26B A4B IT better than GPT-5.3 Codex?

Which is cheaper, Gemma 4 26B A4B IT or GPT-5.3 Codex?

Gemma 4 26B A4B IT is cheaper. It lists at $0.0675 per million input tokens and $0.23 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.

Is Gemma 4 26B A4B IT or GPT-5.3 Codex better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 39.0 in the Noometry coding category.

Which has the bigger context window?

GPT-5.3 Codex does, with 400K tokens against 262K.

How many benchmarks do Gemma 4 26B A4B IT and GPT-5.3 Codex share?

4 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and GPT-5.3 Codex has 8.