Noometry

Model comparison

Grok-3 mini vs Mistral Small

Grok-3 mini is the stronger model overall, scoring 41.0 to 33.1 on the Noometry Index.

Last verified . 21 shared benchmarks.

Grok-3 mini xAI

41.0

Rank #130 Confirmed

Mistral Small Mistral AI

33.1

Rank #238 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Mistral Small in 1 category; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok-3 mini leads 40.3 to 15.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 5.8% for Mistral Small.
  • Mistral Small has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniMistral Small
ProviderxAIMistral AI
Noometry Index41.033.1
Released2025-04-092024-02-26
WeightsProprietaryOpen
Context window—256K
Max output—256K
Input $ / M tokens—$0.15
Output $ / M tokens—$0.60
Results tracked3539

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

Category by category

Coding Grok-3 mini leads

Grok-3 mini: 40.4 (#126), Mistral Small: 33.5 (#242)

BenchmarkGrok-3 miniMistral Small
LMArena Coding13801363
Aider Polyglot49.3%—
SciCode—26.5%
WeirdML42.6%—
BigCodeBench Instruct—36.1%
LiveBench Coding—36.2%
BigCodeBench Complete—46.6%
ALE-Bench—497.62

Agentic & Tool Use Not comparable

Grok-3 mini: —, Mistral Small: 27.9 (#87)

BenchmarkGrok-3 miniMistral Small
Berkeley Function Calling Leaderboard—37.1%

Reasoning Mistral Small leads

Grok-3 mini: 13.8 (#323), Mistral Small: 19.3 (#238)

BenchmarkGrok-3 miniMistral Small
Kagi LLM Benchmark61.3%37.8%
LMArena Hard Prompts13741336
ARC-AGI-20.4%—
ARC-AGI-116.5%—
CritPt—0%
LiveBench Reasoning—44.8%
DTBench—70.9%
LiveBench Data Analysis—53.7%
LMCA—20.6%
Epoch Capabilities Index140.35—
LiveBench—44%

Math Grok-3 mini leads

Grok-3 mini: 40.3 (#78), Mistral Small: 15.4 (#287)

BenchmarkGrok-3 miniMistral Small
OTIS Mock AIME 2024-202577.8%5.8%
LMArena Math13861341
MATH Level 590.9%46.8%
Omni-MATH31.8%—
LiveBench Math—39.9%
FrontierMath (Feb 2025 set)5.9%—

Knowledge Grok-3 mini leads

Grok-3 mini: 46.3 (#75), Mistral Small: 30.9 (#214)

BenchmarkGrok-3 miniMistral Small
GPQA Diamond76.3%47.5%
LMArena Expert13951293
MMLU-Pro79.9%—
Confabulations10.8%—
Vectara Hallucination Rate—5.1%
GPQA (HELM)67.5%—
MMLU—68.7%

Multimodal Not comparable

Grok-3 mini: —, Mistral Small: 32.9 (#91)

BenchmarkGrok-3 miniMistral Small
LMArena Vision—1142

Multilingual Grok-3 mini leads

Grok-3 mini: 48.3 (#141), Mistral Small: 45.7 (#164)

BenchmarkGrok-3 miniMistral Small
LMArena Non-English13521315
LMArena Chinese13871342
LMArena French13571337
LMArena German13501341
LMArena Japanese13431275
LMArena Korean13361260
LMArena Russian13521324
LMArena Spanish13791346

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.7 (#8), Mistral Small: 66.6 (#204)

BenchmarkGrok-3 miniMistral Small
LMArena Instruction Following13561310
LiveBench Instruction Following—63.7%
IFEval95.1%—

Long Context Too close to call

Grok-3 mini: 41.0 (#142), Mistral Small: 40.4 (#151)

BenchmarkGrok-3 miniMistral Small
LMArena Longer Query13721327
Fiction.LiveBench66.7%—

Writing & Preference Too close to call

Grok-3 mini: 52.7 (#163), Mistral Small: 52.6 (#165)

BenchmarkGrok-3 miniMistral Small
LMArena Text13701338
LMArena Creative Writing13421304
LMArena Multi-Turn13551344
Short-Story Creative Writing73.5%—
WildBench65.1%—
LiveBench Language—30.5%

Frequently asked questions

Is Grok-3 mini better than Mistral Small?

Grok-3 mini is the stronger model overall, scoring 41.0 to 33.1 on the Noometry Index.

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

Grok-3 mini scores higher on coding benchmarks: 40.4 versus 33.5 in the Noometry coding category.

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

21 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Mistral Small has 39.

Related comparisons

Go deeper