Noometry

Model comparison

Granite 4.0 H Small vs Llama 4 Scout

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 27.7 on the Noometry Index.

Last verified . 19 shared benchmarks.

Granite 4.0 H Small IBM

36.5

Rank #214 Confirmed

Llama 4 Scout Meta

27.7

Rank #330 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Granite 4.0 H Small scores higher in 7 categories and Llama 4 Scout in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Granite 4.0 H Small leads 36.4 to 20.2.
  • The biggest single-benchmark swing is MMLU-Pro: 56.9% for Granite 4.0 H Small and 74.2% for Llama 4 Scout.

Side by side

Granite 4.0 H SmallLlama 4 Scout
ProviderIBMMeta
Noometry Index36.527.7
Released—2025-04-05
WeightsOpenOpen
Context window—128K
Max output—4K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.30
Results tracked1943

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

Category by category

Coding Granite 4.0 H Small leads

Granite 4.0 H Small: 36.4 (#209), Llama 4 Scout: 20.2 (#339)

BenchmarkGranite 4.0 H SmallLlama 4 Scout
LMArena Coding12491286
SWE-bench Verified (bash only)—9.1%
SciCode—17%
BigCodeBench Complete—43.1%

Agentic & Tool Use Not comparable

Granite 4.0 H Small: —, Llama 4 Scout: 24.6 (#119)

BenchmarkGranite 4.0 H SmallLlama 4 Scout
Berkeley Function Calling Leaderboard—28.1%

Reasoning Granite 4.0 H Small leads

Granite 4.0 H Small: 24.4 (#163), Llama 4 Scout: 9.1 (#345)

BenchmarkGranite 4.0 H SmallLlama 4 Scout
LMArena Hard Prompts12401266
ARC-AGI-2—0%
Kagi LLM Benchmark—36.9%
ARC-AGI-1—0.5%
CritPt—0%
DTBench—57.9%
LMCA—12%
Epoch Capabilities Index—129.64
ForecastBench—57.5

Math Granite 4.0 H Small leads

Granite 4.0 H Small: 31.4 (#223), Llama 4 Scout: 19.6 (#286)

BenchmarkGranite 4.0 H SmallLlama 4 Scout
Omni-MATH29.6%37.3%
LMArena Math12471287
OTIS Mock AIME 2024-2025—7.8%
MATH Level 5—62.3%
FrontierMath (Feb 2025 set)—0%

Knowledge Too close to call

Granite 4.0 H Small: 32.0 (#215), Llama 4 Scout: 31.9 (#217)

BenchmarkGranite 4.0 H SmallLlama 4 Scout
MMLU-Pro56.9%74.2%
Vectara Hallucination Rate5.2%7.7%
GPQA (HELM)38.3%50.7%
LMArena Expert12511235
GPQA Diamond—51.8%

Multimodal Not comparable

Granite 4.0 H Small: —, Llama 4 Scout: 32.2 (#102)

BenchmarkGranite 4.0 H SmallLlama 4 Scout
LMArena Vision—1118
SpatialViz-Bench—34.2%

Multilingual Llama 4 Scout leads

Granite 4.0 H Small: 38.6 (#228), Llama 4 Scout: 41.0 (#212)

BenchmarkGranite 4.0 H SmallLlama 4 Scout
LMArena Non-English12161252
LMArena Chinese12491255
LMArena Russian12011263
LMArena Spanish12581278
LMArena French—1282
LMArena German—1272
LMArena Japanese—1206
LMArena Korean—1207

Instruction Following Granite 4.0 H Small leads

Granite 4.0 H Small: 68.7 (#183), Llama 4 Scout: 65.8 (#217)

BenchmarkGranite 4.0 H SmallLlama 4 Scout
IFEval89%81.8%
LMArena Instruction Following12221248

Long Context Granite 4.0 H Small leads

Granite 4.0 H Small: 37.7 (#213), Llama 4 Scout: 27.5 (#294)

BenchmarkGranite 4.0 H SmallLlama 4 Scout
LMArena Longer Query12421265
Fiction.LiveBench—36%

Writing & Preference Granite 4.0 H Small leads

Granite 4.0 H Small: 43.8 (#227), Llama 4 Scout: 37.0 (#261)

BenchmarkGranite 4.0 H SmallLlama 4 Scout
LMArena Text12411279
LMArena Creative Writing12111249
WildBench73.9%78%
LMArena Multi-Turn12421280
EQ-Bench Creative Writing—783

Frequently asked questions

Is Granite 4.0 H Small better than Llama 4 Scout?

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 27.7 on the Noometry Index.

Is Granite 4.0 H Small or Llama 4 Scout better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 20.2 in the Noometry coding category.

How many benchmarks do Granite 4.0 H Small and Llama 4 Scout share?

19 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Llama 4 Scout has 43.

Related comparisons

Go deeper