Noometry

Model comparison

Amazon Nova Micro vs Granite 4.0 H Small

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 30.4 on the Noometry Index.

Last verified . 19 shared benchmarks.

Amazon Nova Micro Amazon

30.4

Rank #294 Confirmed

Granite 4.0 H Small IBM

36.5

Rank #214 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and Granite 4.0 H Small in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where Granite 4.0 H Small leads 68.7 to 56.3.
  • The biggest single-benchmark swing is IFEval: 76% for Amazon Nova Micro and 89% for Granite 4.0 H Small.
  • Granite 4.0 H Small has downloadable open weights; the other is API-only.

Side by side

Amazon Nova MicroGranite 4.0 H Small
ProviderAmazonIBM
Noometry Index30.436.5
Released2024-12-03—
WeightsProprietaryOpen
Context window128K—
Max output10K—
Input $ / M tokens$0.035—
Output $ / M tokens$0.14—
Results tracked3219

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

Category by category

Coding Granite 4.0 H Small leads

Amazon Nova Micro: 30.5 (#295), Granite 4.0 H Small: 36.4 (#209)

BenchmarkAmazon Nova MicroGranite 4.0 H Small
LMArena Coding12181249
LiveBench Coding20.2%—

Agentic & Tool Use Not comparable

Amazon Nova Micro: 22.1 (#132), Granite 4.0 H Small: —

BenchmarkAmazon Nova MicroGranite 4.0 H Small
Berkeley Function Calling Leaderboard22.3%—

Reasoning Granite 4.0 H Small leads

Amazon Nova Micro: 17.4 (#294), Granite 4.0 H Small: 24.4 (#163)

BenchmarkAmazon Nova MicroGranite 4.0 H Small
LMArena Hard Prompts11911240
LiveBench Reasoning25.1%—
LiveBench Data Analysis34%—
LiveBench29.6%—

Math Granite 4.0 H Small leads

Amazon Nova Micro: 26.9 (#254), Granite 4.0 H Small: 31.4 (#223)

BenchmarkAmazon Nova MicroGranite 4.0 H Small
Omni-MATH21.4%29.6%
LMArena Math12061247
LiveBench Math34.5%—

Knowledge Granite 4.0 H Small leads

Amazon Nova Micro: 29.6 (#237), Granite 4.0 H Small: 32.0 (#215)

BenchmarkAmazon Nova MicroGranite 4.0 H Small
MMLU-Pro51.1%56.9%
Vectara Hallucination Rate5.5%5.2%
GPQA (HELM)38.3%38.3%
LMArena Expert11841251
MMLU70.8%—

Multilingual Granite 4.0 H Small leads

Amazon Nova Micro: 36.5 (#239), Granite 4.0 H Small: 38.6 (#228)

BenchmarkAmazon Nova MicroGranite 4.0 H Small
LMArena Non-English11861216
LMArena Chinese12091249
LMArena Russian11851201
LMArena Spanish12251258
LMArena French1238—
LMArena German1192—
LMArena Japanese1154—
LMArena Korean1150—

Instruction Following Granite 4.0 H Small leads

Amazon Nova Micro: 56.3 (#272), Granite 4.0 H Small: 68.7 (#183)

BenchmarkAmazon Nova MicroGranite 4.0 H Small
IFEval76%89%
LMArena Instruction Following11741222
LiveBench Instruction Following48%—

Long Context Granite 4.0 H Small leads

Amazon Nova Micro: 36.5 (#229), Granite 4.0 H Small: 37.7 (#213)

BenchmarkAmazon Nova MicroGranite 4.0 H Small
LMArena Longer Query12051242

Writing & Preference Granite 4.0 H Small leads

Amazon Nova Micro: 39.5 (#247), Granite 4.0 H Small: 43.8 (#227)

BenchmarkAmazon Nova MicroGranite 4.0 H Small
LMArena Text12081241
LMArena Creative Writing11721211
WildBench74.3%73.9%
LMArena Multi-Turn11781242
LiveBench Language15.8%—

Frequently asked questions

Is Amazon Nova Micro better than Granite 4.0 H Small?

Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 30.4 on the Noometry Index.

Is Amazon Nova Micro or Granite 4.0 H Small better for coding?

Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 30.5 in the Noometry coding category.

How many benchmarks do Amazon Nova Micro and Granite 4.0 H Small share?

19 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Granite 4.0 H Small has 19.

Related comparisons

Go deeper