Noometry

Model comparison

Gemma 4 26B A4B IT vs GPT-5-Codex

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 37.9 on the Noometry Index.

Last verified . 1 shared benchmarks.

Gemma 4 26B A4B IT Google

43.5

Rank #92 Confirmed

GPT-5-Codex OpenAI

37.9

Rank #192 Reported

Summary

  • They share 1 benchmark with published results for both. Gemma 4 26B A4B IT scores higher in 0 categories and GPT-5-Codex in 2 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5-Codex leads 30.9 to 21.8.
  • The biggest single-benchmark swing is WeirdML: 35.2% for Gemma 4 26B A4B IT and 54.5% for GPT-5-Codex.
  • Gemma 4 26B A4B IT is cheaper at $0.0675 / $0.23 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
  • GPT-5-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 ITGPT-5-Codex
ProviderGoogleOpenAI
Noometry Index43.537.9
Released2026-04-022025-09-15
WeightsOpenProprietary
Context window262K400K
Max output33K128K
Input $ / M tokens$0.0675$1.25
Output $ / M tokens$0.23$10
Results tracked283

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

Category by category

Coding GPT-5-Codex leads

Gemma 4 26B A4B IT: 39.0 (#164), GPT-5-Codex: 42.4 (#103)

BenchmarkGemma 4 26B A4B ITGPT-5-Codex
WeirdML35.2%54.5%
LMArena WebDev1359—
SciCode40%—
LMArena Coding1447—
ALE-Bench927.17—

Agentic & Tool Use Not comparable

Gemma 4 26B A4B IT: —, GPT-5-Codex: 31.0 (#72)

BenchmarkGemma 4 26B A4B ITGPT-5-Codex
Terminal-Bench—44.3%

Reasoning GPT-5-Codex leads

Gemma 4 26B A4B IT: 21.8 (#213), GPT-5-Codex: 30.9 (#83)

BenchmarkGemma 4 26B A4B ITGPT-5-Codex
Kagi LLM Benchmark—70.3%
CritPt0%—
Chess Puzzles6%—
LMArena Hard Prompts1439—
DTBench74.9%—
LMCA29.7%—
Epoch Capabilities Index141.85—

Math Not comparable

Gemma 4 26B A4B IT: 47.6 (#67), GPT-5-Codex: —

BenchmarkGemma 4 26B A4B ITGPT-5-Codex
OTIS Mock AIME 2024-202582.2%—
LMArena Math1470—

Knowledge Not comparable

Gemma 4 26B A4B IT: 45.7 (#85), GPT-5-Codex: —

BenchmarkGemma 4 26B A4B ITGPT-5-Codex
GPQA Diamond73.2%—
Vectara Hallucination Rate5.2%—
LMArena Expert1447—

Multimodal Not comparable

Gemma 4 26B A4B IT: 40.6 (#46), GPT-5-Codex: —

BenchmarkGemma 4 26B A4B ITGPT-5-Codex
LMArena Vision1260—

Multilingual Not comparable

Gemma 4 26B A4B IT: 53.1 (#71), GPT-5-Codex: —

BenchmarkGemma 4 26B A4B ITGPT-5-Codex
LMArena Non-English1421—
LMArena Chinese1495—
LMArena French1460—
LMArena Russian1434—
LMArena Spanish1417—

Instruction Following Not comparable

Gemma 4 26B A4B IT: 74.8 (#82), GPT-5-Codex: —

BenchmarkGemma 4 26B A4B ITGPT-5-Codex
LMArena Instruction Following1420—

Long Context Not comparable

Gemma 4 26B A4B IT: 43.6 (#91), GPT-5-Codex: —

BenchmarkGemma 4 26B A4B ITGPT-5-Codex
LMArena Longer Query1428—

Writing & Preference Not comparable

Gemma 4 26B A4B IT: 58.6 (#115), GPT-5-Codex: —

BenchmarkGemma 4 26B A4B ITGPT-5-Codex
LMArena Text1434—
LMArena Creative Writing1402—
EQ-Bench Creative Writing1305—
LMArena Multi-Turn1441—

Frequently asked questions

Is Gemma 4 26B A4B IT better than GPT-5-Codex?

Gemma 4 26B A4B IT is the stronger model overall, scoring 43.5 to 37.9 on the Noometry Index.

Which is cheaper, Gemma 4 26B A4B IT or GPT-5-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-Codex lists at $1.25 and $10.

Is Gemma 4 26B A4B IT or GPT-5-Codex better for coding?

GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 39.0 in the Noometry coding category.

Which has the bigger context window?

GPT-5-Codex does, with 400K tokens against 262K.

How many benchmarks do Gemma 4 26B A4B IT and GPT-5-Codex share?

1 benchmark has published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and GPT-5-Codex has 3.

Related comparisons

Go deeper