Noometry

Model comparison

Gemma 4 31B IT vs GPT-5.3 Chat

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 42.1 on the Noometry Index.

Last verified . 15 shared benchmarks.

Gemma 4 31B IT Google

43.2

Rank #85 Confirmed

GPT-5.3 Chat OpenAI

42.1

Rank #109 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Gemma 4 31B IT scores higher in 5 categories and GPT-5.3 Chat in 3 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemma 4 31B IT leads 41.3 to 35.4.
  • Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Chat.
  • Gemma 4 31B IT accepts more context: 262K tokens versus 128K.
  • Gemma 4 31B IT has downloadable open weights; the other is API-only.

Side by side

Gemma 4 31B ITGPT-5.3 Chat
ProviderGoogleOpenAI
Noometry Index43.242.1
Released2026-04-022026-03-03
WeightsOpenProprietary
Context window262K128K
Max output33K16K
Input $ / M tokens$0.09$1.75
Output $ / M tokens$0.34$14
Results tracked3518

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

Category by category

Coding Gemma 4 31B IT leads

Gemma 4 31B IT: 41.9 (#98), GPT-5.3 Chat: 40.8 (#124)

BenchmarkGemma 4 31B ITGPT-5.3 Chat
LMArena Coding14591408
LMArena WebDev1364—
SciCode43.4%—
WeirdML52.3%—
ALE-Bench925.5—

Reasoning Too close to call

Gemma 4 31B IT: 26.4 (#119), GPT-5.3 Chat: 27.3 (#105)

BenchmarkGemma 4 31B ITGPT-5.3 Chat
LMArena Hard Prompts14481399
Kagi LLM Benchmark63.5%—
NYT Connections (extended)70.6%—
CritPt1.4%—
Chess Puzzles5%—
Thematic Generalization53%—
DTBench82.7%—
LMCA39.3%—
Surface Evolver Bench30.6%—
Epoch Capabilities Index142.74—

Math Gemma 4 31B IT leads

Gemma 4 31B IT: 41.3 (#72), GPT-5.3 Chat: 35.4 (#146)

BenchmarkGemma 4 31B ITGPT-5.3 Chat
LMArena Math14641389
OTIS Mock AIME 2024-202573.3%—

Knowledge Too close to call

Gemma 4 31B IT: 37.9 (#141), GPT-5.3 Chat: 38.2 (#137)

BenchmarkGemma 4 31B ITGPT-5.3 Chat
LMArena Expert14651397
GPQA Diamond75.8%—
SimpleQA Verified10.4%—
Vectara Hallucination Rate7.4%—

Multimodal Not comparable

Gemma 4 31B IT: 41.0 (#32), GPT-5.3 Chat: —

BenchmarkGemma 4 31B ITGPT-5.3 Chat
LMArena Vision1278—
LMArena Document1425—

Multilingual Gemma 4 31B IT leads

Gemma 4 31B IT: 54.0 (#52), GPT-5.3 Chat: 50.5 (#119)

BenchmarkGemma 4 31B ITGPT-5.3 Chat
LMArena Non-English14311383
LMArena Chinese14781433
LMArena French14361398
LMArena Russian14621400
LMArena Spanish14431371
LMArena German—1384
LMArena Japanese—1351
LMArena Korean—1347

Instruction Following Gemma 4 31B IT leads

Gemma 4 31B IT: 75.6 (#58), GPT-5.3 Chat: 73.0 (#124)

BenchmarkGemma 4 31B ITGPT-5.3 Chat
LMArena Instruction Following14331378

Long Context Gemma 4 31B IT leads

Gemma 4 31B IT: 44.2 (#67), GPT-5.3 Chat: 42.6 (#115)

BenchmarkGemma 4 31B ITGPT-5.3 Chat
LMArena Longer Query14461396

Writing & Preference GPT-5.3 Chat leads

Gemma 4 31B IT: 60.7 (#92), GPT-5.3 Chat: 63.3 (#65)

BenchmarkGemma 4 31B ITGPT-5.3 Chat
LMArena Text14431389
LMArena Creative Writing14161356
EQ-Bench Creative Writing13681690
LMArena Multi-Turn14521413
EQ-Bench 41120—

Frequently asked questions

Is Gemma 4 31B IT better than GPT-5.3 Chat?

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 42.1 on the Noometry Index.

Which is cheaper, Gemma 4 31B IT or GPT-5.3 Chat?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; GPT-5.3 Chat lists at $1.75 and $14.

Is Gemma 4 31B IT or GPT-5.3 Chat better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 40.8 in the Noometry coding category.

Which has the bigger context window?

Gemma 4 31B IT does, with 262K tokens against 128K.

How many benchmarks do Gemma 4 31B IT and GPT-5.3 Chat share?

15 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and GPT-5.3 Chat has 18.

Related comparisons

Go deeper