Noometry

Model comparison

Gemma 3 4B vs GPT-5.4 Pro

GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 28.1 on the Noometry Index. Gemma 3 4B costs 1350× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.

Last verified . 4 shared benchmarks.

Gemma 3 4B Google

28.1

Rank #326 Confirmed

GPT-5.4 Pro OpenAI

58.9

Rank #18 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and GPT-5.4 Pro in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 13.2.
  • The biggest single-benchmark swing is GPQA Diamond: 23.2% for Gemma 3 4B and 94.6% for GPT-5.4 Pro.
  • Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
  • GPT-5.4 Pro accepts more context: 1.05M tokens versus 131K.
  • Gemma 3 4B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 4BGPT-5.4 Pro
ProviderGoogleOpenAI
Noometry Index28.158.9
Released2025-03-122026-03-05
WeightsOpenProprietary
Context window131K1.05M
Max output4K128K
Input $ / M tokens$0.04$30
Output $ / M tokens$0.08$180
Results tracked2216

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

Category by category

Coding GPT-5.4 Pro leads

Gemma 3 4B: 35.9 (#215), GPT-5.4 Pro: 43.2 (#90)

BenchmarkGemma 3 4BGPT-5.4 Pro
WeirdML—57.4%
LMArena Coding1230—

Agentic & Tool Use Not comparable

Gemma 3 4B: 20.9 (#142), GPT-5.4 Pro: —

BenchmarkGemma 3 4BGPT-5.4 Pro
Berkeley Function Calling Leaderboard19.6%—

Reasoning GPT-5.4 Pro leads

Gemma 3 4B: 13.2 (#335), GPT-5.4 Pro: 70.7 (#13)

BenchmarkGemma 3 4BGPT-5.4 Pro
Chess Puzzles0%58.6%
Epoch Capabilities Index116.02158.93
ARC-AGI-2—83.3%
SimpleBench—74.1%
Kagi LLM Benchmark25.2%—
ARC-AGI-1—94.5%
CritPt—30%
EnigmaEval—23.8%
LMArena Hard Prompts1253—
DTBench50.9%—
LMCA2.8%—

Math GPT-5.4 Pro leads

Gemma 3 4B: 16.8 (#292), GPT-5.4 Pro: 72.4 (#22)

BenchmarkGemma 3 4BGPT-5.4 Pro
FrontierMath (Tiers 1-3)—82.5%
FrontierMath Tier 4—58.5%
OTIS Mock AIME 2024-20257.5%—
LMArena Math1239—
FrontierMath (Feb 2025 set)—50%
FrontierMath Tier 4 (v1)—37.5%

Knowledge GPT-5.4 Pro leads

Gemma 3 4B: 11.8 (#299), GPT-5.4 Pro: 68.3 (#7)

BenchmarkGemma 3 4BGPT-5.4 Pro
GPQA Diamond23.2%94.6%
Vectara Hallucination Rate6.4%8.3%
Humanity's Last Exam—44.3%
SimpleQA Verified—46.3%
LMArena Expert1223—

Multilingual Not comparable

Gemma 3 4B: 42.5 (#194), GPT-5.4 Pro: —

BenchmarkGemma 3 4BGPT-5.4 Pro
LMArena Non-English1273—
LMArena German1281—
LMArena Russian1294—

Instruction Following Not comparable

Gemma 3 4B: 65.2 (#225), GPT-5.4 Pro: —

BenchmarkGemma 3 4BGPT-5.4 Pro
LMArena Instruction Following1239—

Long Context Not comparable

Gemma 3 4B: 38.7 (#194), GPT-5.4 Pro: —

BenchmarkGemma 3 4BGPT-5.4 Pro
LMArena Longer Query1273—

Writing & Preference Not comparable

Gemma 3 4B: 42.0 (#239), GPT-5.4 Pro: —

BenchmarkGemma 3 4BGPT-5.4 Pro
LMArena Text1291—
LMArena Creative Writing1271—
EQ-Bench Creative Writing1068—
LMArena Multi-Turn1255—

Frequently asked questions

Is Gemma 3 4B better than GPT-5.4 Pro?

GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 28.1 on the Noometry Index. Gemma 3 4B costs 1350× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.

Which is cheaper, Gemma 3 4B or GPT-5.4 Pro?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GPT-5.4 Pro lists at $30 and $180.

Is Gemma 3 4B or GPT-5.4 Pro better for coding?

GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 35.9 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 Pro does, with 1.05M tokens against 131K.

How many benchmarks do Gemma 3 4B and GPT-5.4 Pro share?

4 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and GPT-5.4 Pro has 16.

Related comparisons

Go deeper