Noometry

Model comparison

Grok-3 mini vs Mistral Large

Grok-3 mini is the stronger model overall, scoring 41.2 to 31.9 on the Noometry Index.

Last verified . 29 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Mistral Large Mistral AI

31.9

Rank #263 Confirmed

Summary

  • They share 29 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Mistral Large in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok-3 mini leads 42.1 to 18.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 8.5% for Mistral Large.
  • Mistral Large has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniMistral Large
ProviderxAIMistral AI
Noometry Index41.231.9
Released2025-04-092024-02-26
WeightsProprietaryOpen
Context window—131K
Max output—16K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3551

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

Category by category

Coding Grok-3 mini leads

Grok-3 mini: 40.8 (#131), Mistral Large: 34.3 (#240)

BenchmarkGrok-3 miniMistral Large
LMArena Coding13791277
Aider Polyglot49.3%—
SciCode—36.2%
WeirdML42.6%—
BigCodeBench Instruct—30%
LiveBench Coding—47.1%
BigCodeBench Complete—38.3%
ALE-Bench—264.7
HumanEval+—62.2%
MBPP+—59.5%

Agentic & Tool Use Not comparable

Grok-3 mini: —, Mistral Large: 28.6 (#89)

BenchmarkGrok-3 miniMistral Large
Berkeley Function Calling Leaderboard—38.4%

Reasoning Mistral Large leads

Grok-3 mini: 13.6 (#334), Mistral Large: 15.8 (#310)

BenchmarkGrok-3 miniMistral Large
LMArena Hard Prompts13751257
Epoch Capabilities Index140.35128.52
ARC-AGI-20.4%—
SimpleBench—22.5%
Kagi LLM Benchmark61.3%—
ARC-AGI-116.5%—
CritPt—0%
LiveBench Reasoning—43.5%
DTBench—65.1%
LiveBench Data Analysis—50.1%
LMCA—16.7%
ForecastBench—57.1
LiveBench—48.4%

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), Mistral Large: 18.2 (#291)

BenchmarkGrok-3 miniMistral Large
OTIS Mock AIME 2024-202577.8%8.5%
Omni-MATH31.8%28.1%
LMArena Math13861262
MATH Level 590.9%50.3%
FrontierMath (Feb 2025 set)5.9%0.3%
LiveBench Math—42.5%

Knowledge Grok-3 mini leads

Grok-3 mini: 46.4 (#81), Mistral Large: 30.1 (#230)

BenchmarkGrok-3 miniMistral Large
GPQA Diamond76.3%51.3%
MMLU-Pro79.9%59.9%
Confabulations10.8%21.4%
GPQA (HELM)67.5%43.5%
LMArena Expert13951232
Vectara Hallucination Rate—4.5%
MMLU—80%

Multilingual Grok-3 mini leads

Grok-3 mini: 48.1 (#145), Mistral Large: 40.0 (#219)

BenchmarkGrok-3 miniMistral Large
LMArena Non-English13521237
LMArena Chinese13871240
LMArena French13571325
LMArena German13491254
LMArena Japanese13421188
LMArena Korean13351202
LMArena Russian13531257
LMArena Spanish13811268

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Mistral Large: 67.9 (#191)

BenchmarkGrok-3 miniMistral Large
IFEval95.1%87.7%
LMArena Instruction Following13571249
LiveBench Instruction Following—67.9%

Long Context Grok-3 mini leads

Grok-3 mini: 41.0 (#147), Mistral Large: 38.3 (#199)

BenchmarkGrok-3 miniMistral Large
LMArena Longer Query13721261
Fiction.LiveBench66.7%—

Writing & Preference Grok-3 mini leads

Grok-3 mini: 52.5 (#169), Mistral Large: 40.7 (#242)

BenchmarkGrok-3 miniMistral Large
LMArena Text13701266
LMArena Creative Writing13421243
Short-Story Creative Writing73.5%69%
WildBench65.1%80.1%
LMArena Multi-Turn13551260
EQ-Bench Creative Writing—985
LiveBench Language—39.4%

Frequently asked questions

Is Grok-3 mini better than Mistral Large?

Grok-3 mini is the stronger model overall, scoring 41.2 to 31.9 on the Noometry Index.

Is Grok-3 mini or Mistral Large better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 34.3 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Mistral Large share?

29 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Mistral Large has 51.

Related comparisons

Go deeper