Noometry

Model comparison

Gemma 4 31B IT vs GPT-5-Codex

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 37.9 on the Noometry Index.

Last verified . 2 shared benchmarks.

Gemma 4 31B IT Google

43.5

Rank #90 Confirmed

GPT-5-Codex OpenAI

37.9

Rank #192 Reported

Summary

  • They share 2 benchmarks with published results for both. Gemma 4 31B IT scores higher in 0 categories and GPT-5-Codex in 2 categories; one gap is clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5-Codex leads 30.9 to 27.2.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 63.5% for Gemma 4 31B IT and 70.3% for GPT-5-Codex.
  • Gemma 4 31B IT is cheaper at $0.09 / $0.34 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 31B IT has downloadable open weights; the other is API-only.

Side by side

Gemma 4 31B ITGPT-5-Codex
ProviderGoogleOpenAI
Noometry Index43.537.9
Released2026-04-022025-09-15
WeightsOpenProprietary
Context window262K400K
Max output33K128K
Input $ / M tokens$0.09$1.25
Output $ / M tokens$0.34$10
Results tracked353

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

Category by category

Coding Too close to call

Gemma 4 31B IT: 42.3 (#108), GPT-5-Codex: 42.4 (#103)

BenchmarkGemma 4 31B ITGPT-5-Codex
WeirdML52.3%54.5%
LMArena WebDev1366—
SciCode43.4%—
LMArena Coding1459—
ALE-Bench925.5—

Agentic & Tool Use Not comparable

Gemma 4 31B IT: —, GPT-5-Codex: 31.0 (#72)

BenchmarkGemma 4 31B ITGPT-5-Codex
Terminal-Bench—44.3%

Reasoning GPT-5-Codex leads

Gemma 4 31B IT: 27.2 (#122), GPT-5-Codex: 30.9 (#83)

BenchmarkGemma 4 31B ITGPT-5-Codex
Kagi LLM Benchmark63.5%70.3%
NYT Connections (extended)70.6%—
CritPt1.4%—
Chess Puzzles5%—
Thematic Generalization53%—
LMArena Hard Prompts1448—
DTBench82.7%—
LMCA39.3%—
Surface Evolver Bench30.6%—
Epoch Capabilities Index142.74—

Math Not comparable

Gemma 4 31B IT: 43.2 (#81), GPT-5-Codex: —

BenchmarkGemma 4 31B ITGPT-5-Codex
OTIS Mock AIME 2024-202573.3%—
LMArena Math1465—

Knowledge Not comparable

Gemma 4 31B IT: 37.9 (#151), GPT-5-Codex: —

BenchmarkGemma 4 31B ITGPT-5-Codex
GPQA Diamond75.8%—
SimpleQA Verified10.4%—
Vectara Hallucination Rate7.4%—
LMArena Expert1465—

Multimodal Not comparable

Gemma 4 31B IT: 41.6 (#34), GPT-5-Codex: —

BenchmarkGemma 4 31B ITGPT-5-Codex
LMArena Vision1277—
LMArena Document1425—

Multilingual Not comparable

Gemma 4 31B IT: 53.8 (#57), GPT-5-Codex: —

BenchmarkGemma 4 31B ITGPT-5-Codex
LMArena Non-English1431—
LMArena Chinese1476—
LMArena French1435—
LMArena Russian1460—
LMArena Spanish1444—

Instruction Following Not comparable

Gemma 4 31B IT: 75.5 (#61), GPT-5-Codex: —

BenchmarkGemma 4 31B ITGPT-5-Codex
LMArena Instruction Following1433—

Long Context Not comparable

Gemma 4 31B IT: 44.2 (#71), GPT-5-Codex: —

BenchmarkGemma 4 31B ITGPT-5-Codex
LMArena Longer Query1446—

Writing & Preference Not comparable

Gemma 4 31B IT: 60.5 (#96), GPT-5-Codex: —

BenchmarkGemma 4 31B ITGPT-5-Codex
LMArena Text1443—
LMArena Creative Writing1415—
EQ-Bench Creative Writing1368—
EQ-Bench 41120—
LMArena Multi-Turn1452—

Frequently asked questions

Is Gemma 4 31B IT better than GPT-5-Codex?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 37.9 on the Noometry Index.

Which is cheaper, Gemma 4 31B IT or GPT-5-Codex?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; GPT-5-Codex lists at $1.25 and $10.

Is Gemma 4 31B IT or GPT-5-Codex better for coding?

They score almost the same on coding (42.3 vs 42.4); test both on your own repository before choosing.

Which has the bigger context window?

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

How many benchmarks do Gemma 4 31B IT and GPT-5-Codex share?

2 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and GPT-5-Codex has 3.

Related comparisons

Go deeper