Noometry

Model comparison

GPT-4 vs Mistral Large 3

Mistral Large 3 is the stronger model overall, scoring 39.1 to 29.1 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Mistral Large 3 Mistral AI

39.1

Rank #176 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-4 scores higher in 1 category and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Mistral Large 3 leads 38.7 to 10.8.
  • Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $30 / $60 for GPT-4.
  • Mistral Large 3 accepts more context: 262K tokens versus 8K.
  • Mistral Large 3 has downloadable open weights; the other is API-only.

Side by side

GPT-4Mistral Large 3
ProviderOpenAIMistral AI
Noometry Index29.139.1
Released2023-03-142025-12-02
WeightsProprietaryOpen
Context window8K262K
Max output8K8K
Input $ / M tokens$30$0.25
Output $ / M tokens$60$0.75
Results tracked3824

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

Category by category

Coding Mistral Large 3 leads

GPT-4: 31.6 (#283), Mistral Large 3: 34.4 (#237)

BenchmarkGPT-4Mistral Large 3
LMArena Coding12541448
LMArena WebDev—1230
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Mistral Large 3: —

BenchmarkGPT-4Mistral Large 3
METR Time Horizons36.1%—

Reasoning GPT-4 leads

GPT-4: 17.8 (#289), Mistral Large 3: 15.2 (#319)

BenchmarkGPT-4Mistral Large 3
LMArena Hard Prompts12411429
Kagi LLM Benchmark—50.9%
NYT Connections (extended)—7.5%
Chess Puzzles4%—
Thematic Generalization—23%
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.89—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Mistral Large 3 leads

GPT-4: 10.8 (#309), Mistral Large 3: 38.7 (#129)

BenchmarkGPT-4Mistral Large 3
LMArena Math12691414
OTIS Mock AIME 2024-20251.1%—
MATH Level 523%—
GSM8K92%—

Knowledge Mistral Large 3 leads

GPT-4: 18.4 (#282), Mistral Large 3: 36.0 (#177)

BenchmarkGPT-4Mistral Large 3
LMArena Expert12111421
GPQA Diamond35.7%—
Vectara Hallucination Rate—14.5%
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Mistral Large 3: 38.2 (#66)

BenchmarkGPT-4Mistral Large 3
LMArena Vision—1221

Multilingual Mistral Large 3 leads

GPT-4: 40.6 (#215), Mistral Large 3: 52.5 (#84)

BenchmarkGPT-4Mistral Large 3
LMArena Non-English12461413
LMArena Chinese12421447
LMArena French12831455
LMArena German12511437
LMArena Japanese12091394
LMArena Korean11841384
LMArena Russian12511411
LMArena Spanish12611440

Instruction Following Mistral Large 3 leads

GPT-4: 65.3 (#222), Mistral Large 3: 74.0 (#108)

BenchmarkGPT-4Mistral Large 3
LMArena Instruction Following12411403

Long Context Mistral Large 3 leads

GPT-4: 37.7 (#212), Mistral Large 3: 43.1 (#105)

BenchmarkGPT-4Mistral Large 3
LMArena Longer Query12441413

Writing & Preference Mistral Large 3 leads

GPT-4: 34.9 (#268), Mistral Large 3: 60.0 (#101)

BenchmarkGPT-4Mistral Large 3
LMArena Text12631428
LMArena Creative Writing12441386
EQ-Bench Creative Writing7521412
LMArena Multi-Turn12571429

Frequently asked questions

Is GPT-4 better than Mistral Large 3?

Mistral Large 3 is the stronger model overall, scoring 39.1 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Mistral Large 3?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Mistral Large 3 better for coding?

Mistral Large 3 scores higher on coding benchmarks: 34.4 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 8K.

How many benchmarks do GPT-4 and Mistral Large 3 share?

18 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Mistral Large 3 has 24.

Related comparisons

Go deeper