Noometry

Model comparison

Mistral 7B vs Mistral Small 3.2

Mistral Small 3.2 is the stronger model overall, scoring 31.2 to 23.0 on the Noometry Index.

Last verified . 4 shared benchmarks.

Mistral 7B Mistral AI

23.0

Rank #351 Confirmed

Mistral Small 3.2 Mistral AI

31.2

Rank #280 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Mistral Small 3.2 in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Mistral Small 3.2 leads 26.7 to 7.4.
  • The biggest single-benchmark swing is GPQA Diamond: 15.2% for Mistral 7B and 49.1% for Mistral Small 3.2.
  • Mistral Small 3.2 is cheaper at $0.0938 / $0.25 per million input/output tokens, against $0.25 / $0.25 for Mistral 7B.
  • Mistral Small 3.2 accepts more context: 256K tokens versus 8K.

Side by side

Mistral 7BMistral Small 3.2
ProviderMistral AIMistral AI
Noometry Index23.031.2
Released2023-09-272025-06-20
WeightsOpenOpen
Context window8K256K
Max output8K16K
Input $ / M tokens$0.25$0.0938
Output $ / M tokens$0.25$0.25
Results tracked376

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

Category by category

Coding Not comparable

Mistral 7B: 26.4 (#326), Mistral Small 3.2: —

BenchmarkMistral 7BMistral Small 3.2
BigCodeBench Instruct19.5%—
LMArena Coding1082—
BigCodeBench Complete27.3%—
HumanEval+36%—
MBPP+42.1%—

Reasoning Mistral Small 3.2 leads

Mistral 7B: 13.1 (#336), Mistral Small 3.2: 18.1 (#287)

BenchmarkMistral 7BMistral Small 3.2
Chess Puzzles0%1%
Epoch Capabilities Index112.21131.74
Kagi LLM Benchmark—40.4%
LMArena Hard Prompts1067—
DTBench42.5%—
Adversarial NLI47.1%—
BIG-Bench Hard56.1%—
HellaSwag81%—
PIQA83%—
WinoGrande75.3%—

Math Mistral Small 3.2 leads

Mistral 7B: 8.1 (#325), Mistral Small 3.2: 26.3 (#260)

BenchmarkMistral 7BMistral Small 3.2
OTIS Mock AIME 2024-20250.3%30.3%
LMArena Math1085—
MATH Level 53.7%—
GSM8K54.4%—

Knowledge Mistral Small 3.2 leads

Mistral 7B: 7.4 (#311), Mistral Small 3.2: 26.7 (#256)

BenchmarkMistral 7BMistral Small 3.2
GPQA Diamond15.2%49.1%
LMArena Expert1036—
ARC (AI2) Challenge78.6%—
BoolQ87.4%—
MMLU62.5%—
OpenBookQA79.8%—
TriviaQA75.2%—

Multilingual Not comparable

Mistral 7B: 25.8 (#283), Mistral Small 3.2: —

BenchmarkMistral 7BMistral Small 3.2
LMArena Non-English1012—
LMArena Chinese1009—
LMArena French1037—
LMArena German987—
LMArena Japanese878—
LMArena Russian1018—
LMArena Spanish1026—

Instruction Following Not comparable

Mistral 7B: 54.2 (#280), Mistral Small 3.2: —

BenchmarkMistral 7BMistral Small 3.2
LMArena Instruction Following1060—

Long Context Not comparable

Mistral 7B: 32.2 (#271), Mistral Small 3.2: —

BenchmarkMistral 7BMistral Small 3.2
LMArena Longer Query1060—

Writing & Preference Mistral Small 3.2 leads

Mistral 7B: 30.7 (#286), Mistral Small 3.2: 45.0 (#224)

BenchmarkMistral 7BMistral Small 3.2
LMArena Text1090—
LMArena Creative Writing1068—
EQ-Bench Creative Writing—1255
LMArena Multi-Turn1062—

Frequently asked questions

Is Mistral 7B better than Mistral Small 3.2?

Mistral Small 3.2 is the stronger model overall, scoring 31.2 to 23.0 on the Noometry Index.

Which is cheaper, Mistral 7B or Mistral Small 3.2?

Mistral Small 3.2 is cheaper. It lists at $0.0938 per million input tokens and $0.25 per million output tokens; Mistral 7B lists at $0.25 and $0.25.

Which has the bigger context window?

Mistral Small 3.2 does, with 256K tokens against 8K.

How many benchmarks do Mistral 7B and Mistral Small 3.2 share?

4 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Mistral Small 3.2 has 6.

Related comparisons

Go deeper