Noometry

Model comparison

GPT-4 vs Mistral Small 3.2

Mistral Small 3.2 is the stronger model overall, scoring 31.2 to 29.1 on the Noometry Index.

Last verified . 5 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Mistral Small 3.2 Mistral AI

31.2

Rank #280 Confirmed

Summary

  • They share 5 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Mistral Small 3.2 in 4 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where Mistral Small 3.2 leads 26.3 to 10.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 30.3% for Mistral Small 3.2.
  • Mistral Small 3.2 is cheaper at $0.0938 / $0.25 per million input/output tokens, against $30 / $60 for GPT-4.
  • Mistral Small 3.2 accepts more context: 256K tokens versus 8K.
  • Mistral Small 3.2 has downloadable open weights; the other is API-only.

Side by side

GPT-4Mistral Small 3.2
ProviderOpenAIMistral AI
Noometry Index29.131.2
Released2023-03-142025-06-20
WeightsProprietaryOpen
Context window8K256K
Max output8K16K
Input $ / M tokens$30$0.0938
Output $ / M tokens$60$0.25
Results tracked386

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

Category by category

Coding Not comparable

GPT-4: 31.6 (#283), Mistral Small 3.2: —

BenchmarkGPT-4Mistral Small 3.2
WeirdML12.4%—
BigCodeBench Instruct46%—
LMArena Coding1254—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Mistral Small 3.2: —

BenchmarkGPT-4Mistral Small 3.2
METR Time Horizons36.1%—

Reasoning Too close to call

GPT-4: 17.8 (#289), Mistral Small 3.2: 18.1 (#287)

BenchmarkGPT-4Mistral Small 3.2
Chess Puzzles4%1%
Epoch Capabilities Index125.89131.74
Kagi LLM Benchmark—40.4%
LMArena Hard Prompts1241—
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Mistral Small 3.2 leads

GPT-4: 10.8 (#309), Mistral Small 3.2: 26.3 (#260)

BenchmarkGPT-4Mistral Small 3.2
OTIS Mock AIME 2024-20251.1%30.3%
LMArena Math1269—
MATH Level 523%—
GSM8K92%—

Knowledge Mistral Small 3.2 leads

GPT-4: 18.4 (#282), Mistral Small 3.2: 26.7 (#256)

BenchmarkGPT-4Mistral Small 3.2
GPQA Diamond35.7%49.1%
LMArena Expert1211—
MMLU86.4%—
TriviaQA84.8%—

Multilingual Not comparable

GPT-4: 40.6 (#215), Mistral Small 3.2: —

BenchmarkGPT-4Mistral Small 3.2
LMArena Non-English1246—
LMArena Chinese1242—
LMArena French1283—
LMArena German1251—
LMArena Japanese1209—
LMArena Korean1184—
LMArena Russian1251—
LMArena Spanish1261—

Instruction Following Not comparable

GPT-4: 65.3 (#222), Mistral Small 3.2: —

BenchmarkGPT-4Mistral Small 3.2
LMArena Instruction Following1241—

Long Context Not comparable

GPT-4: 37.7 (#212), Mistral Small 3.2: —

BenchmarkGPT-4Mistral Small 3.2
LMArena Longer Query1244—

Writing & Preference Mistral Small 3.2 leads

GPT-4: 34.9 (#268), Mistral Small 3.2: 45.0 (#224)

BenchmarkGPT-4Mistral Small 3.2
EQ-Bench Creative Writing7521255
LMArena Text1263—
LMArena Creative Writing1244—
LMArena Multi-Turn1257—

Frequently asked questions

Is GPT-4 better than Mistral Small 3.2?

Mistral Small 3.2 is the stronger model overall, scoring 31.2 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 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; GPT-4 lists at $30 and $60.

Which has the bigger context window?

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

How many benchmarks do GPT-4 and Mistral Small 3.2 share?

5 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Mistral Small 3.2 has 6.

Related comparisons

Go deeper