Noometry

Model comparison

Gemma 3 4B vs Mistral 7B

Gemma 3 4B is the stronger model overall, scoring 28.1 to 23.0 on the Noometry Index.

Last verified . 17 shared benchmarks.

Gemma 3 4B Google

28.1

Rank #326 Confirmed

Mistral 7B Mistral AI

23.0

Rank #351 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Gemma 3 4B scores higher in 8 categories and Mistral 7B in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Gemma 3 4B leads 42.5 to 25.8.
  • The biggest single-benchmark swing is DTBench: 50.9% for Gemma 3 4B and 42.5% for Mistral 7B.
  • Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.25 / $0.25 for Mistral 7B.
  • Gemma 3 4B accepts more context: 131K tokens versus 8K.

Side by side

Gemma 3 4BMistral 7B
ProviderGoogleMistral AI
Noometry Index28.123.0
Released2025-03-122023-09-27
WeightsOpenOpen
Context window131K8K
Max output4K8K
Input $ / M tokens$0.04$0.25
Output $ / M tokens$0.08$0.25
Results tracked2237

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), Mistral 7B: 26.4 (#326)

BenchmarkGemma 3 4BMistral 7B
LMArena Coding12301082
BigCodeBench Instruct—19.5%
BigCodeBench Complete—27.3%
HumanEval+—36%
MBPP+—42.1%

Agentic & Tool Use Not comparable

Gemma 3 4B: 20.9 (#142), Mistral 7B: —

BenchmarkGemma 3 4BMistral 7B
Berkeley Function Calling Leaderboard19.6%—

Reasoning Too close to call

Gemma 3 4B: 13.2 (#335), Mistral 7B: 13.1 (#336)

BenchmarkGemma 3 4BMistral 7B
Chess Puzzles0%0%
LMArena Hard Prompts12531067
DTBench50.9%42.5%
Epoch Capabilities Index116.02112.21
Kagi LLM Benchmark25.2%—
LMCA2.8%—
Adversarial NLI—47.1%
BIG-Bench Hard—56.1%
HellaSwag—81%
PIQA—83%
WinoGrande—75.3%

Math Gemma 3 4B leads

Gemma 3 4B: 16.8 (#292), Mistral 7B: 8.1 (#325)

BenchmarkGemma 3 4BMistral 7B
OTIS Mock AIME 2024-20257.5%0.3%
LMArena Math12391085
MATH Level 5—3.7%
GSM8K—54.4%

Knowledge Gemma 3 4B leads

Gemma 3 4B: 11.8 (#299), Mistral 7B: 7.4 (#311)

BenchmarkGemma 3 4BMistral 7B
GPQA Diamond23.2%15.2%
LMArena Expert12231036
Vectara Hallucination Rate6.4%—
ARC (AI2) Challenge—78.6%
BoolQ—87.4%
MMLU—62.5%
OpenBookQA—79.8%
TriviaQA—75.2%

Multilingual Gemma 3 4B leads

Gemma 3 4B: 42.5 (#194), Mistral 7B: 25.8 (#283)

BenchmarkGemma 3 4BMistral 7B
LMArena Non-English12731012
LMArena German1281987
LMArena Russian12941018
LMArena Chinese—1009
LMArena French—1037
LMArena Japanese—878
LMArena Spanish—1026

Instruction Following Gemma 3 4B leads

Gemma 3 4B: 65.2 (#225), Mistral 7B: 54.2 (#280)

BenchmarkGemma 3 4BMistral 7B
LMArena Instruction Following12391060

Long Context Gemma 3 4B leads

Gemma 3 4B: 38.7 (#194), Mistral 7B: 32.2 (#271)

BenchmarkGemma 3 4BMistral 7B
LMArena Longer Query12731060

Writing & Preference Gemma 3 4B leads

Gemma 3 4B: 42.0 (#239), Mistral 7B: 30.7 (#286)

BenchmarkGemma 3 4BMistral 7B
LMArena Text12911090
LMArena Creative Writing12711068
LMArena Multi-Turn12551062
EQ-Bench Creative Writing1068—

Frequently asked questions

Is Gemma 3 4B better than Mistral 7B?

Gemma 3 4B is the stronger model overall, scoring 28.1 to 23.0 on the Noometry Index.

Which is cheaper, Gemma 3 4B or Mistral 7B?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Mistral 7B lists at $0.25 and $0.25.

Is Gemma 3 4B or Mistral 7B better for coding?

Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 26.4 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 Mistral 7B share?

17 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Mistral 7B has 37.

Related comparisons

Go deeper