Noometry

Model comparison

Grok-2 (Dec 2024) vs Phi 3 Small 8k Instruct

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 29.3 on the Noometry Index.

Last verified . 24 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Phi 3 Small 8k Instruct Microsoft

29.3

Rank #314 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 7 categories and Phi 3 Small 8k Instruct in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Grok-2 (Dec 2024) leads 48.6 to 31.1.
  • The biggest single-benchmark swing is LiveBench Reasoning: 54.8% for Grok-2 (Dec 2024) and 15.9% for Phi 3 Small 8k Instruct.
  • Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Phi 3 Small 8k Instruct
ProviderxAIMicrosoft
Noometry Index33.729.3
Released2024-08-132024-04-23
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3432

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

Category by category

Coding Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 33.3 (#258), Phi 3 Small 8k Instruct: 27.9 (#318)

BenchmarkGrok-2 (Dec 2024)Phi 3 Small 8k Instruct
LiveBench Coding46.4%20.3%
LMArena Coding12871101
WeirdML22.2%—

Reasoning Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 16.9 (#299), Phi 3 Small 8k Instruct: 14.8 (#323)

BenchmarkGrok-2 (Dec 2024)Phi 3 Small 8k Instruct
LiveBench Reasoning54.8%15.9%
LMArena Hard Prompts12721100
LiveBench Data Analysis54.5%30.3%
LiveBench54.3%24%
SimpleBench22.7%—
DTBench65.2%—
Adversarial NLI—58.1%
BIG-Bench Hard—79.1%
Epoch Capabilities Index130.48—
HellaSwag—77%
WinoGrande—81.5%

Math Phi 3 Small 8k Instruct leads

Grok-2 (Dec 2024): 20.8 (#284), Phi 3 Small 8k Instruct: 27.6 (#248)

BenchmarkGrok-2 (Dec 2024)Phi 3 Small 8k Instruct
LiveBench Math54.9%17.6%
LMArena Math12831151
OTIS Mock AIME 2024-202511.5%—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Too close to call

Grok-2 (Dec 2024): 29.8 (#233), Phi 3 Small 8k Instruct: 29.1 (#240)

BenchmarkGrok-2 (Dec 2024)Phi 3 Small 8k Instruct
LMArena Expert12541067
GPQA Diamond53.8%—
Confabulations20.1%—
ARC (AI2) Challenge—90.7%
MMLU—75.7%
OpenBookQA—88%
TriviaQA—58.1%

Multilingual Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 43.1 (#188), Phi 3 Small 8k Instruct: 28.5 (#272)

BenchmarkGrok-2 (Dec 2024)Phi 3 Small 8k Instruct
LMArena Non-English12821058
LMArena Chinese12891061
LMArena French13181135
LMArena German12871080
LMArena Japanese1244966
LMArena Korean1237894
LMArena Russian12861111
LMArena Spanish12811111

Instruction Following Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 66.9 (#202), Phi 3 Small 8k Instruct: 51.9 (#292)

BenchmarkGrok-2 (Dec 2024)Phi 3 Small 8k Instruct
LiveBench Instruction Following69.6%47.2%
LMArena Instruction Following12701087

Long Context Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 38.8 (#190), Phi 3 Small 8k Instruct: 33.0 (#267)

BenchmarkGrok-2 (Dec 2024)Phi 3 Small 8k Instruct
LMArena Longer Query12761088

Writing & Preference Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 48.6 (#198), Phi 3 Small 8k Instruct: 31.1 (#284)

BenchmarkGrok-2 (Dec 2024)Phi 3 Small 8k Instruct
LMArena Text13051110
LMArena Creative Writing12841083
LMArena Multi-Turn12901068
LiveBench Language45.6%12.9%
Short-Story Creative Writing63.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Phi 3 Small 8k Instruct?

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 29.3 on the Noometry Index.

Is Grok-2 (Dec 2024) or Phi 3 Small 8k Instruct better for coding?

Grok-2 (Dec 2024) scores higher on coding benchmarks: 33.3 versus 27.9 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Phi 3 Small 8k Instruct share?

24 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Phi 3 Small 8k Instruct has 32.

Related comparisons

Go deeper