Noometry

Model comparison

GPT-4 vs Mistral Large 4

Mistral Large 4 is the stronger model overall, scoring 43.1 to 29.1 on the Noometry Index.

Last verified . 12 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Mistral Large 4 Mistral AI

43.1

Rank #99 Confirmed

Summary

  • They share 12 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Mistral Large 4 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Mistral Large 4 leads 40.4 to 10.8.
  • Mistral Large 4 is cheaper at $0.68 / $2.09 per million input/output tokens, against $30 / $60 for GPT-4.
  • Mistral Large 4 accepts more context: 1.05M tokens versus 8K.

Side by side

GPT-4Mistral Large 4
ProviderOpenAIMistral AI
Noometry Index29.143.1
Released2023-03-142026-10-06
WeightsProprietaryProprietary
Context window8K1.05M
Max output8K262K
Input $ / M tokens$30$0.68
Output $ / M tokens$60$2.09
Results tracked3815

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

Category by category

Coding Mistral Large 4 leads

GPT-4: 31.6 (#283), Mistral Large 4: 48.6 (#57)

BenchmarkGPT-4Mistral Large 4
LMArena Coding12541475
LMArena WebDev—1541
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Mistral Large 4: —

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

Reasoning Mistral Large 4 leads

GPT-4: 17.8 (#289), Mistral Large 4: 22.5 (#192)

BenchmarkGPT-4Mistral Large 4
LMArena Hard Prompts12411444
NYT Connections (extended)—27.4%
Chess Puzzles4%—
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.89—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Mistral Large 4 leads

GPT-4: 10.8 (#309), Mistral Large 4: 40.4 (#91)

BenchmarkGPT-4Mistral Large 4
LMArena Math12691488
OTIS Mock AIME 2024-20251.1%—
MATH Level 523%—
GSM8K92%—

Knowledge Mistral Large 4 leads

GPT-4: 18.4 (#282), Mistral Large 4: 36.6 (#166)

BenchmarkGPT-4Mistral Large 4
LMArena Expert12111447
GPQA Diamond35.7%—
SimpleQA Verified—20%
MMLU86.4%—
TriviaQA84.8%—

Multilingual Mistral Large 4 leads

GPT-4: 40.6 (#215), Mistral Large 4: 52.6 (#82)

BenchmarkGPT-4Mistral Large 4
LMArena Non-English12461415
LMArena Chinese12421491
LMArena Russian12511414
LMArena French1283—
LMArena German1251—
LMArena Japanese1209—
LMArena Korean1184—
LMArena Spanish1261—

Instruction Following Mistral Large 4 leads

GPT-4: 65.3 (#222), Mistral Large 4: 75.0 (#76)

BenchmarkGPT-4Mistral Large 4
LMArena Instruction Following12411424

Long Context Mistral Large 4 leads

GPT-4: 37.7 (#212), Mistral Large 4: 43.6 (#89)

BenchmarkGPT-4Mistral Large 4
LMArena Longer Query12441429

Writing & Preference Mistral Large 4 leads

GPT-4: 34.9 (#268), Mistral Large 4: 60.4 (#97)

BenchmarkGPT-4Mistral Large 4
LMArena Text12631427
LMArena Creative Writing12441361
LMArena Multi-Turn12571424
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Mistral Large 4?

Mistral Large 4 is the stronger model overall, scoring 43.1 to 29.1 on the Noometry Index.

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

Mistral Large 4 is cheaper. It lists at $0.68 per million input tokens and $2.09 per million output tokens; GPT-4 lists at $30 and $60.

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

Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Mistral Large 4 does, with 1.05M tokens against 8K.

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

12 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Mistral Large 4 has 15.

Related comparisons

Go deeper