Noometry

Model comparison

Grok 4 vs Mistral Medium 3.5

Grok 4 is the stronger model overall, scoring 48.1 to 40.2 on the Noometry Index.

Last verified . 19 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

Mistral Medium 3.5 Mistral AI

40.2

Rank #152 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Grok 4 scores higher in 6 categories and Mistral Medium 3.5 in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 43.2.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 73.6% for Grok 4 and 41.4% for Mistral Medium 3.5.
  • Mistral Medium 3.5 has downloadable open weights; the other is API-only.

Side by side

Grok 4Mistral Medium 3.5
ProviderxAIMistral AI
Noometry Index48.140.2
Released2025-07-09—
WeightsProprietaryOpen
Context window—262K
Max output—210K
Input $ / M tokens—$1.50
Output $ / M tokens—$7.50
Results tracked4822

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 Medium 3.5: 36.0 (#213)

BenchmarkGrok 4Mistral Medium 3.5
LMArena Coding14081461
Aider Polyglot79.6%—
LMArena WebDev—1264
WeirdML45.7%—

Agentic & Tool Use Not comparable

Grok 4: 32.3 (#68), Mistral Medium 3.5: —

BenchmarkGrok 4Mistral Medium 3.5
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 Medium 3.5: 17.3 (#295)

BenchmarkGrok 4Mistral Medium 3.5
Kagi LLM Benchmark73.6%41.4%
LMArena Hard Prompts14091436
Epoch Capabilities Index146.44141.35
ARC-AGI-216%—
SimpleBench60.5%—
NYT Connections (extended)—12.9%
ARC-AGI-166.7%—
Chess Puzzles28%—
ForecastBench60.9—

Math Grok 4 leads

Grok 4: 48.4 (#64), Mistral Medium 3.5: 39.1 (#113)

BenchmarkGrok 4Mistral Medium 3.5
LMArena Math14221431
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 Medium 3.5: 40.0 (#126)

BenchmarkGrok 4Mistral Medium 3.5
LMArena Expert14151432
GPQA Diamond87%—
MMLU-Pro85.1%—
Confabulations12.4%—
GPQA (HELM)72.7%—

Multimodal Mistral Medium 3.5 leads

Grok 4: 33.7 (#94), Mistral Medium 3.5: 38.3 (#65)

BenchmarkGrok 4Mistral Medium 3.5
LMArena Vision12101223
GeoBench45%—

Multilingual Too close to call

Grok 4: 51.8 (#103), Mistral Medium 3.5: 51.9 (#100)

BenchmarkGrok 4Mistral Medium 3.5
LMArena Non-English14031404
LMArena Chinese14271442
LMArena French14181448
LMArena German14291451
LMArena Korean13771385
LMArena Russian14101395
LMArena Spanish14201409
LMArena Japanese1394—

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), Mistral Medium 3.5: 74.6 (#90)

BenchmarkGrok 4Mistral Medium 3.5
LMArena Instruction Following13871415
IFEval94.9%—

Long Context Grok 4 leads

Grok 4: 63.1 (#4), Mistral Medium 3.5: 43.2 (#103)

BenchmarkGrok 4Mistral Medium 3.5
LMArena Longer Query14091415
Fiction.LiveBench94.4%—

Writing & Preference Too close to call

Grok 4: 58.5 (#116), Mistral Medium 3.5: 58.5 (#117)

BenchmarkGrok 4Mistral Medium 3.5
LMArena Text14111421
LMArena Creative Writing13971374
LMArena Multi-Turn14161423
Short-Story Creative Writing76.9%—
WildBench79.7%—
EQ-Bench 4—993

Frequently asked questions

Is Grok 4 better than Mistral Medium 3.5?

Grok 4 is the stronger model overall, scoring 48.1 to 40.2 on the Noometry Index.

Is Grok 4 or Mistral Medium 3.5 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 36.0 in the Noometry coding category.

How many benchmarks do Grok 4 and Mistral Medium 3.5 share?

19 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and Mistral Medium 3.5 has 22.

Related comparisons

Go deeper