Noometry

Model comparison

Grok-3 mini vs Phi 3 Small 8k Instruct

Grok-3 mini is the stronger model overall, scoring 41.2 to 29.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Phi 3 Small 8k Instruct Microsoft

29.3

Rank #314 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Phi 3 Small 8k Instruct in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where Grok-3 mini leads 78.5 to 51.9.
  • Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniPhi 3 Small 8k Instruct
ProviderxAIMicrosoft
Noometry Index41.229.3
Released2025-04-092024-04-23
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3532

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), Phi 3 Small 8k Instruct: 27.9 (#318)

BenchmarkGrok-3 miniPhi 3 Small 8k Instruct
LMArena Coding13791101
Aider Polyglot49.3%—
WeirdML42.6%—
LiveBench Coding—20.3%

Reasoning Phi 3 Small 8k Instruct leads

Grok-3 mini: 13.6 (#334), Phi 3 Small 8k Instruct: 14.8 (#323)

BenchmarkGrok-3 miniPhi 3 Small 8k Instruct
LMArena Hard Prompts13751100
ARC-AGI-20.4%—
Kagi LLM Benchmark61.3%—
ARC-AGI-116.5%—
LiveBench Reasoning—15.9%
LiveBench Data Analysis—30.3%
Adversarial NLI—58.1%
BIG-Bench Hard—79.1%
Epoch Capabilities Index140.35—
HellaSwag—77%
LiveBench—24%
WinoGrande—81.5%

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), Phi 3 Small 8k Instruct: 27.6 (#248)

BenchmarkGrok-3 miniPhi 3 Small 8k Instruct
LMArena Math13861151
OTIS Mock AIME 2024-202577.8%—
Omni-MATH31.8%—
LiveBench Math—17.6%
MATH Level 590.9%—
FrontierMath (Feb 2025 set)5.9%—

Knowledge Grok-3 mini leads

Grok-3 mini: 46.4 (#81), Phi 3 Small 8k Instruct: 29.1 (#240)

BenchmarkGrok-3 miniPhi 3 Small 8k Instruct
LMArena Expert13951067
GPQA Diamond76.3%—
MMLU-Pro79.9%—
Confabulations10.8%—
GPQA (HELM)67.5%—
ARC (AI2) Challenge—90.7%
MMLU—75.7%
OpenBookQA—88%
TriviaQA—58.1%

Multilingual Grok-3 mini leads

Grok-3 mini: 48.1 (#145), Phi 3 Small 8k Instruct: 28.5 (#272)

BenchmarkGrok-3 miniPhi 3 Small 8k Instruct
LMArena Non-English13521058
LMArena Chinese13871061
LMArena French13571135
LMArena German13491080
LMArena Japanese1342966
LMArena Korean1335894
LMArena Russian13531111
LMArena Spanish13811111

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Phi 3 Small 8k Instruct: 51.9 (#292)

BenchmarkGrok-3 miniPhi 3 Small 8k Instruct
LMArena Instruction Following13571087
LiveBench Instruction Following—47.2%
IFEval95.1%—

Long Context Grok-3 mini leads

Grok-3 mini: 41.0 (#147), Phi 3 Small 8k Instruct: 33.0 (#267)

BenchmarkGrok-3 miniPhi 3 Small 8k Instruct
LMArena Longer Query13721088
Fiction.LiveBench66.7%—

Writing & Preference Grok-3 mini leads

Grok-3 mini: 52.5 (#169), Phi 3 Small 8k Instruct: 31.1 (#284)

BenchmarkGrok-3 miniPhi 3 Small 8k Instruct
LMArena Text13701110
LMArena Creative Writing13421083
LMArena Multi-Turn13551068
Short-Story Creative Writing73.5%—
WildBench65.1%—
LiveBench Language—12.9%

Frequently asked questions

Is Grok-3 mini better than Phi 3 Small 8k Instruct?

Grok-3 mini is the stronger model overall, scoring 41.2 to 29.3 on the Noometry Index.

Is Grok-3 mini or Phi 3 Small 8k Instruct better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 27.9 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Phi 3 Small 8k Instruct share?

17 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Phi 3 Small 8k Instruct has 32.

Related comparisons

Go deeper