Noometry

Model comparison

Mistral 7B vs Mistral Small 3

Mistral Small 3 is the stronger model overall, scoring 31.2 to 23.0 on the Noometry Index.

Last verified . 21 shared benchmarks.

Mistral 7B Mistral AI

23.0

Rank #351 Confirmed

Mistral Small 3 Mistral AI

31.2

Rank #278 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Mistral Small 3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Mistral Small 3 leads 25.1 to 7.4.
  • The biggest single-benchmark swing is GPQA Diamond: 15.2% for Mistral 7B and 47.3% for Mistral Small 3.
  • Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.25 / $0.25 for Mistral 7B.
  • Mistral Small 3 accepts more context: 33K tokens versus 8K.

Side by side

Mistral 7BMistral Small 3
ProviderMistral AIMistral AI
Noometry Index23.031.2
Released2023-09-272025-01-30
WeightsOpenOpen
Context window8K33K
Max output8K16K
Input $ / M tokens$0.25$0.05
Output $ / M tokens$0.25$0.08
Results tracked3724

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

Category by category

Coding Mistral Small 3 leads

Mistral 7B: 26.4 (#326), Mistral Small 3: 36.5 (#207)

BenchmarkMistral 7BMistral Small 3
BigCodeBench Instruct19.5%45.3%
LMArena Coding10821246
BigCodeBench Complete27.3%50.4%
HumanEval+36%—
MBPP+42.1%—

Reasoning Mistral Small 3 leads

Mistral 7B: 13.1 (#336), Mistral Small 3: 18.9 (#273)

BenchmarkMistral 7BMistral Small 3
Chess Puzzles0%0%
LMArena Hard Prompts10671233
Epoch Capabilities Index112.21127.07
DTBench42.5%—
Adversarial NLI47.1%—
BIG-Bench Hard56.1%—
HellaSwag81%—
PIQA83%—
WinoGrande75.3%—

Math Mistral Small 3 leads

Mistral 7B: 8.1 (#325), Mistral Small 3: 16.3 (#295)

BenchmarkMistral 7BMistral Small 3
OTIS Mock AIME 2024-20250.3%6.7%
LMArena Math10851240
MATH Level 53.7%—
GSM8K54.4%—

Knowledge Mistral Small 3 leads

Mistral 7B: 7.4 (#311), Mistral Small 3: 25.1 (#263)

BenchmarkMistral 7BMistral Small 3
GPQA Diamond15.2%47.3%
LMArena Expert10361202
Confabulations—25.2%
ARC (AI2) Challenge78.6%—
BoolQ87.4%—
MMLU62.5%—
OpenBookQA79.8%—
TriviaQA75.2%—

Multilingual Mistral Small 3 leads

Mistral 7B: 25.8 (#283), Mistral Small 3: 37.3 (#236)

BenchmarkMistral 7BMistral Small 3
LMArena Non-English10121198
LMArena Chinese10091204
LMArena French10371203
LMArena German9871211
LMArena Japanese8781111
LMArena Russian10181216
LMArena Korean—1188
LMArena Spanish1026—

Instruction Following Mistral Small 3 leads

Mistral 7B: 54.2 (#280), Mistral Small 3: 63.7 (#229)

BenchmarkMistral 7BMistral Small 3
LMArena Instruction Following10601214

Long Context Mistral Small 3 leads

Mistral 7B: 32.2 (#271), Mistral Small 3: 37.8 (#211)

BenchmarkMistral 7BMistral Small 3
LMArena Longer Query10601246

Writing & Preference Mistral Small 3 leads

Mistral 7B: 30.7 (#286), Mistral Small 3: 32.2 (#280)

BenchmarkMistral 7BMistral Small 3
LMArena Text10901234
LMArena Creative Writing10681195
LMArena Multi-Turn10621217
EQ-Bench Creative Writing—707

Frequently asked questions

Is Mistral 7B better than Mistral Small 3?

Mistral Small 3 is the stronger model overall, scoring 31.2 to 23.0 on the Noometry Index.

Which is cheaper, Mistral 7B or Mistral Small 3?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Mistral 7B lists at $0.25 and $0.25.

Is Mistral 7B or Mistral Small 3 better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 26.4 in the Noometry coding category.

Which has the bigger context window?

Mistral Small 3 does, with 33K tokens against 8K.

How many benchmarks do Mistral 7B and Mistral Small 3 share?

21 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Mistral Small 3 has 24.

Related comparisons

Go deeper