Noometry

Model comparison

Grok 4 vs Mistral Large 3

Grok 4 is the stronger model overall, scoring 48.1 to 39.1 on the Noometry Index.

Last verified . 19 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

Mistral Large 3 Mistral AI

39.1

Rank #176 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Grok 4 scores higher in 6 categories and Mistral Large 3 in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4 leads 36.7 to 15.2.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 73.6% for Grok 4 and 50.9% for Mistral Large 3.
  • Mistral Large 3 has downloadable open weights; the other is API-only.

Side by side

Grok 4Mistral Large 3
ProviderxAIMistral AI
Noometry Index48.139.1
Released2025-07-092025-12-02
WeightsProprietaryOpen
Context window—262K
Max output—8K
Input $ / M tokens—$0.25
Output $ / M tokens—$0.75
Results tracked4824

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

Category by category

Coding Grok 4 leads

Grok 4: 50.3 (#46), Mistral Large 3: 34.4 (#237)

BenchmarkGrok 4Mistral Large 3
LMArena Coding14081448
Aider Polyglot79.6%—
LMArena WebDev—1230
WeirdML45.7%—

Agentic & Tool Use Not comparable

Grok 4: 32.3 (#68), Mistral Large 3: —

BenchmarkGrok 4Mistral Large 3
Terminal-Bench27.2%—
Berkeley Function Calling Leaderboard63%—
GDPval21.1%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
LMArena Search1142—
METR Time Horizons66.6%—

Reasoning Grok 4 leads

Grok 4: 36.7 (#65), Mistral Large 3: 15.2 (#319)

BenchmarkGrok 4Mistral Large 3
Kagi LLM Benchmark73.6%50.9%
LMArena Hard Prompts14091429
ARC-AGI-216%—
SimpleBench60.5%—
NYT Connections (extended)—7.5%
ARC-AGI-166.7%—
Chess Puzzles28%—
Thematic Generalization—23%
Epoch Capabilities Index146.44—
ForecastBench60.9—

Math Grok 4 leads

Grok 4: 48.4 (#64), Mistral Large 3: 38.7 (#129)

BenchmarkGrok 4Mistral Large 3
LMArena Math14221414
OTIS Mock AIME 2024-202584%—
Omni-MATH60.3%—
FrontierMath (Feb 2025 set)19.7%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Grok 4 leads

Grok 4: 53.8 (#55), Mistral Large 3: 36.0 (#177)

BenchmarkGrok 4Mistral Large 3
LMArena Expert14151421
GPQA Diamond87%—
MMLU-Pro85.1%—
Confabulations12.4%—
Vectara Hallucination Rate—14.5%
GPQA (HELM)72.7%—

Multimodal Mistral Large 3 leads

Grok 4: 33.7 (#94), Mistral Large 3: 38.2 (#66)

BenchmarkGrok 4Mistral Large 3
LMArena Vision12101221
GeoBench45%—

Multilingual Too close to call

Grok 4: 51.8 (#103), Mistral Large 3: 52.5 (#84)

BenchmarkGrok 4Mistral Large 3
LMArena Non-English14031413
LMArena Chinese14271447
LMArena French14181455
LMArena German14291437
LMArena Japanese13941394
LMArena Korean13771384
LMArena Russian14101411
LMArena Spanish14201440

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), Mistral Large 3: 74.0 (#108)

BenchmarkGrok 4Mistral Large 3
LMArena Instruction Following13871403
IFEval94.9%—

Long Context Grok 4 leads

Grok 4: 63.1 (#4), Mistral Large 3: 43.1 (#105)

BenchmarkGrok 4Mistral Large 3
LMArena Longer Query14091413
Fiction.LiveBench94.4%—

Writing & Preference Mistral Large 3 leads

Grok 4: 58.5 (#116), Mistral Large 3: 60.0 (#101)

BenchmarkGrok 4Mistral Large 3
LMArena Text14111428
LMArena Creative Writing13971386
LMArena Multi-Turn14161429
Short-Story Creative Writing76.9%—
EQ-Bench Creative Writing—1412
WildBench79.7%—

Frequently asked questions

Is Grok 4 better than Mistral Large 3?

Grok 4 is the stronger model overall, scoring 48.1 to 39.1 on the Noometry Index.

Is Grok 4 or Mistral Large 3 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 34.4 in the Noometry coding category.

How many benchmarks do Grok 4 and Mistral Large 3 share?

19 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Mistral Large 3 has 24.

Related comparisons

Go deeper