Noometry

Model comparison

Gemma 3 4B vs GPT-4

Gemma 3 4B and GPT-4 score almost the same on the Noometry Index (28.1 vs 29.1), so choose on price, context window or the category you care about most.

Last verified . 19 shared benchmarks.

Gemma 3 4B Google

28.1

Rank #326 Confirmed

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Gemma 3 4B scores higher in 5 categories and GPT-4 in 3 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemma 3 4B leads 42.0 to 34.9.
  • The biggest single-benchmark swing is LMCA: 2.8% for Gemma 3 4B and 17.1% for GPT-4.
  • Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $30 / $60 for GPT-4.
  • Gemma 3 4B accepts more context: 131K tokens versus 8K.
  • Gemma 3 4B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 4BGPT-4
ProviderGoogleOpenAI
Noometry Index28.129.1
Released2025-03-122023-03-14
WeightsOpenProprietary
Context window131K8K
Max output4K8K
Input $ / M tokens$0.04$30
Output $ / M tokens$0.08$60
Results tracked2238

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

Category by category

Coding Gemma 3 4B leads

Gemma 3 4B: 35.9 (#215), GPT-4: 31.6 (#283)

BenchmarkGemma 3 4BGPT-4
LMArena Coding12301254
WeirdML—12.4%
BigCodeBench Instruct—46%
BigCodeBench Complete—57.2%
HumanEval+—79.3%

Agentic & Tool Use Not comparable

Gemma 3 4B: 20.9 (#142), GPT-4: —

BenchmarkGemma 3 4BGPT-4
Berkeley Function Calling Leaderboard19.6%—
METR Time Horizons—36.1%

Reasoning GPT-4 leads

Gemma 3 4B: 13.2 (#335), GPT-4: 17.8 (#289)

BenchmarkGemma 3 4BGPT-4
Chess Puzzles0%4%
LMArena Hard Prompts12531241
DTBench50.9%62.7%
LMCA2.8%17.1%
Epoch Capabilities Index116.02125.89
Kagi LLM Benchmark25.2%—
Mystery Game Puzzles—12%
BIG-Bench Hard—75.1%
ForecastBench—57.8
HellaSwag—95.3%
WinoGrande—87.5%

Math Gemma 3 4B leads

Gemma 3 4B: 16.8 (#292), GPT-4: 10.8 (#309)

BenchmarkGemma 3 4BGPT-4
OTIS Mock AIME 2024-20257.5%1.1%
LMArena Math12391269
MATH Level 5—23%
GSM8K—92%

Knowledge GPT-4 leads

Gemma 3 4B: 11.8 (#299), GPT-4: 18.4 (#282)

BenchmarkGemma 3 4BGPT-4
GPQA Diamond23.2%35.7%
LMArena Expert12231211
Vectara Hallucination Rate6.4%—
MMLU—86.4%
TriviaQA—84.8%

Multilingual Gemma 3 4B leads

Gemma 3 4B: 42.5 (#194), GPT-4: 40.6 (#215)

BenchmarkGemma 3 4BGPT-4
LMArena Non-English12731246
LMArena German12811251
LMArena Russian12941251
LMArena Chinese—1242
LMArena French—1283
LMArena Japanese—1209
LMArena Korean—1184
LMArena Spanish—1261

Instruction Following Too close to call

Gemma 3 4B: 65.2 (#225), GPT-4: 65.3 (#222)

BenchmarkGemma 3 4BGPT-4
LMArena Instruction Following12391241

Long Context Too close to call

Gemma 3 4B: 38.7 (#194), GPT-4: 37.7 (#212)

BenchmarkGemma 3 4BGPT-4
LMArena Longer Query12731244

Writing & Preference Gemma 3 4B leads

Gemma 3 4B: 42.0 (#239), GPT-4: 34.9 (#268)

BenchmarkGemma 3 4BGPT-4
LMArena Text12911263
LMArena Creative Writing12711244
EQ-Bench Creative Writing1068752
LMArena Multi-Turn12551257

Frequently asked questions

Is Gemma 3 4B better than GPT-4?

Gemma 3 4B and GPT-4 score almost the same on the Noometry Index (28.1 vs 29.1), so choose on price, context window or the category you care about most.

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

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GPT-4 lists at $30 and $60.

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

Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Gemma 3 4B does, with 131K tokens against 8K.

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

19 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and GPT-4 has 38.

Related comparisons

Go deeper