Noometry

Model comparison

Grok-2 (Dec 2024) vs Granite 4.0 H Small

Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 33.4 on the Noometry Index.

Last verified . 13 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.4

Rank #233 Confirmed

Granite 4.0 H Small IBM

35.9

Rank #213 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 3 categories and Granite 4.0 H Small in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Granite 4.0 H Small leads 29.3 to 19.6.
  • Granite 4.0 H Small has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Granite 4.0 H Small
ProviderxAIIBM
Noometry Index33.435.9
Released2024-08-13—
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3419

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

Category by category

Coding Granite 4.0 H Small leads

Grok-2 (Dec 2024): 32.9 (#254), Granite 4.0 H Small: 35.8 (#207)

BenchmarkGrok-2 (Dec 2024)Granite 4.0 H Small
LMArena Coding12881247
WeirdML22.2%—
LiveBench Coding46.4%—

Reasoning Granite 4.0 H Small leads

Grok-2 (Dec 2024): 16.4 (#294), Granite 4.0 H Small: 23.4 (#164)

BenchmarkGrok-2 (Dec 2024)Granite 4.0 H Small
LMArena Hard Prompts12721240
SimpleBench22.7%—
LiveBench Reasoning54.8%—
DTBench65.2%—
LiveBench Data Analysis54.5%—
Epoch Capabilities Index130.48—
LiveBench54.3%—

Math Granite 4.0 H Small leads

Grok-2 (Dec 2024): 19.6 (#278), Granite 4.0 H Small: 29.3 (#219)

BenchmarkGrok-2 (Dec 2024)Granite 4.0 H Small
LMArena Math12831251
OTIS Mock AIME 2024-202511.5%—
Omni-MATH—29.6%
LiveBench Math54.9%—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Granite 4.0 H Small leads

Grok-2 (Dec 2024): 29.8 (#225), Granite 4.0 H Small: 31.5 (#210)

BenchmarkGrok-2 (Dec 2024)Granite 4.0 H Small
LMArena Expert12541244
GPQA Diamond53.8%—
MMLU-Pro—56.9%
Confabulations20.1%—
Vectara Hallucination Rate—5.2%
GPQA (HELM)—38.3%

Multilingual Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 43.3 (#183), Granite 4.0 H Small: 38.7 (#223)

BenchmarkGrok-2 (Dec 2024)Granite 4.0 H Small
LMArena Non-English12821216
LMArena Chinese12891250
LMArena Russian12861198
LMArena Spanish12811258
LMArena French1317—
LMArena German1287—
LMArena Japanese1244—
LMArena Korean1237—

Instruction Following Granite 4.0 H Small leads

Grok-2 (Dec 2024): 67.1 (#197), Granite 4.0 H Small: 68.9 (#178)

BenchmarkGrok-2 (Dec 2024)Granite 4.0 H Small
LMArena Instruction Following12701221
LiveBench Instruction Following69.6%—
IFEval—89%

Long Context Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 38.7 (#186), Granite 4.0 H Small: 37.6 (#209)

BenchmarkGrok-2 (Dec 2024)Granite 4.0 H Small
LMArena Longer Query12761240

Writing & Preference Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 48.8 (#192), Granite 4.0 H Small: 44.0 (#222)

BenchmarkGrok-2 (Dec 2024)Granite 4.0 H Small
LMArena Text13051241
LMArena Creative Writing12841210
LMArena Multi-Turn12901243
Short-Story Creative Writing63.6%—
WildBench—73.9%
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Granite 4.0 H Small?

Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 33.4 on the Noometry Index.

Is Grok-2 (Dec 2024) or Granite 4.0 H Small better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 32.9 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Granite 4.0 H Small share?

13 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Granite 4.0 H Small has 19.

Related comparisons

Go deeper