Noometry

Model comparison

Mistral Small 3 vs Mixtral 8x7B

Mistral Small 3 is the stronger model overall, scoring 31.2 to 27.1 on the Noometry Index.

Last verified . 18 shared benchmarks.

Mistral Small 3 Mistral AI

31.2

Rank #278 Confirmed

Mixtral 8x7B Mistral AI

27.1

Rank #334 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Mistral Small 3 scores higher in 6 categories and Mixtral 8x7B in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Mistral Small 3 leads 25.1 to 11.0.
  • The biggest single-benchmark swing is GPQA Diamond: 47.3% for Mistral Small 3 and 30.6% for Mixtral 8x7B.
  • Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
  • Mistral Small 3 accepts more context: 33K tokens versus 32K.

Side by side

Mistral Small 3Mixtral 8x7B
ProviderMistral AIMistral AI
Noometry Index31.227.1
Released2025-01-302023-12-11
WeightsOpenOpen
Context window33K32K
Max output16K32K
Input $ / M tokens$0.05$0.70
Output $ / M tokens$0.08$0.70
Results tracked2438

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

Category by category

Coding Mistral Small 3 leads

Mistral Small 3: 36.5 (#207), Mixtral 8x7B: 32.8 (#269)

BenchmarkMistral Small 3Mixtral 8x7B
LMArena Coding12461126
BigCodeBench Instruct45.3%—
BigCodeBench Complete50.4%—
HumanEval+—39.6%
MBPP+—49.7%

Reasoning Too close to call

Mistral Small 3: 18.9 (#273), Mixtral 8x7B: 18.2 (#285)

BenchmarkMistral Small 3Mixtral 8x7B
LMArena Hard Prompts12331115
Epoch Capabilities Index127.07118.47
Chess Puzzles0%—
DTBench—49.6%
Adversarial NLI—55.2%
ForecastBench—56.3
HellaSwag—86.7%
PIQA—83.6%
WinoGrande—77.2%

Math Mixtral 8x7B leads

Mistral Small 3: 16.3 (#295), Mixtral 8x7B: 18.8 (#289)

BenchmarkMistral Small 3Mixtral 8x7B
LMArena Math12401147
OTIS Mock AIME 2024-20256.7%—
Omni-MATH—10.5%
MATH Level 5—10%
GSM8K—74.4%

Knowledge Mistral Small 3 leads

Mistral Small 3: 25.1 (#263), Mixtral 8x7B: 11.0 (#301)

BenchmarkMistral Small 3Mixtral 8x7B
GPQA Diamond47.3%30.6%
LMArena Expert12021088
MMLU-Pro—33.5%
Confabulations25.2%—
GPQA (HELM)—29.6%
ARC (AI2) Challenge—87.3%
MMLU—70.6%
OpenBookQA—85.8%
TriviaQA—82.2%

Multilingual Mistral Small 3 leads

Mistral Small 3: 37.3 (#236), Mixtral 8x7B: 29.6 (#266)

BenchmarkMistral Small 3Mixtral 8x7B
LMArena Non-English11981077
LMArena Chinese12041055
LMArena French12031166
LMArena German12111114
LMArena Japanese1111931
LMArena Korean1188968
LMArena Russian12161090
LMArena Spanish—1111

Instruction Following Mistral Small 3 leads

Mistral Small 3: 63.7 (#229), Mixtral 8x7B: 51.0 (#297)

BenchmarkMistral Small 3Mixtral 8x7B
LMArena Instruction Following12141109
IFEval—57.5%

Long Context Mistral Small 3 leads

Mistral Small 3: 37.8 (#211), Mixtral 8x7B: 33.4 (#260)

BenchmarkMistral Small 3Mixtral 8x7B
LMArena Longer Query12461103

Writing & Preference Mixtral 8x7B leads

Mistral Small 3: 32.2 (#280), Mixtral 8x7B: 34.2 (#270)

BenchmarkMistral Small 3Mixtral 8x7B
LMArena Text12341132
LMArena Creative Writing11951109
LMArena Multi-Turn12171115
EQ-Bench Creative Writing707—
WildBench—67.3%

Frequently asked questions

Is Mistral Small 3 better than Mixtral 8x7B?

Mistral Small 3 is the stronger model overall, scoring 31.2 to 27.1 on the Noometry Index.

Which is cheaper, Mistral Small 3 or Mixtral 8x7B?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Mixtral 8x7B lists at $0.70 and $0.70.

Is Mistral Small 3 or Mixtral 8x7B better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 32.8 in the Noometry coding category.

Which has the bigger context window?

Mistral Small 3 does, with 33K tokens against 32K.

How many benchmarks do Mistral Small 3 and Mixtral 8x7B share?

18 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Mixtral 8x7B has 38.

Related comparisons

Go deeper