Noometry

Model comparison

Amazon Nova Micro vs Granite 3.1 8b Instruct

Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 29.9 on the Noometry Index.

Last verified . 13 shared benchmarks.

Amazon Nova Micro Amazon

29.9

Rank #290 Confirmed

Granite 3.1 8b Instruct IBM

31.8

Rank #256 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Amazon Nova Micro scores higher in 3 categories and Granite 3.1 8b Instruct in 6 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Amazon Nova Micro leads 36.7 to 31.1.
  • Granite 3.1 8b Instruct has downloadable open weights; the other is API-only.

Side by side

Amazon Nova MicroGranite 3.1 8b Instruct
ProviderAmazonIBM
Noometry Index29.931.8
Released2024-12-03—
WeightsProprietaryOpen
Context window128K—
Max output10K—
Input $ / M tokens$0.035—
Output $ / M tokens$0.14—
Results tracked3213

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

Category by category

Coding Granite 3.1 8b Instruct leads

Amazon Nova Micro: 30.0 (#289), Granite 3.1 8b Instruct: 33.9 (#232)

BenchmarkAmazon Nova MicroGranite 3.1 8b Instruct
LMArena Coding12181186
LiveBench Coding20.2%—

Agentic & Tool Use Granite 3.1 8b Instruct leads

Amazon Nova Micro: 21.9 (#125), Granite 3.1 8b Instruct: 23.9 (#113)

BenchmarkAmazon Nova MicroGranite 3.1 8b Instruct
Berkeley Function Calling Leaderboard22.3%27.1%

Reasoning Granite 3.1 8b Instruct leads

Amazon Nova Micro: 16.7 (#289), Granite 3.1 8b Instruct: 21.2 (#204)

BenchmarkAmazon Nova MicroGranite 3.1 8b Instruct
LMArena Hard Prompts11911146
LiveBench Reasoning25.1%—
LiveBench Data Analysis34%—
LiveBench29.6%—

Math Granite 3.1 8b Instruct leads

Amazon Nova Micro: 24.9 (#252), Granite 3.1 8b Instruct: 30.4 (#210)

BenchmarkAmazon Nova MicroGranite 3.1 8b Instruct
LMArena Math12061152
Omni-MATH21.4%—
LiveBench Math34.5%—

Knowledge Granite 3.1 8b Instruct leads

Amazon Nova Micro: 29.2 (#231), Granite 3.1 8b Instruct: 30.6 (#218)

BenchmarkAmazon Nova MicroGranite 3.1 8b Instruct
LMArena Expert11841142
MMLU-Pro51.1%—
Vectara Hallucination Rate5.5%—
GPQA (HELM)38.3%—
MMLU70.8%—

Multilingual Amazon Nova Micro leads

Amazon Nova Micro: 36.7 (#234), Granite 3.1 8b Instruct: 31.1 (#255)

BenchmarkAmazon Nova MicroGranite 3.1 8b Instruct
LMArena Non-English11861099
LMArena Chinese12091145
LMArena Russian11851092
LMArena French1237—
LMArena German1192—
LMArena Japanese1154—
LMArena Korean1150—
LMArena Spanish1225—

Instruction Following Granite 3.1 8b Instruct leads

Amazon Nova Micro: 56.6 (#267), Granite 3.1 8b Instruct: 58.9 (#254)

BenchmarkAmazon Nova MicroGranite 3.1 8b Instruct
LMArena Instruction Following11741131
LiveBench Instruction Following48%—
IFEval76%—

Long Context Amazon Nova Micro leads

Amazon Nova Micro: 36.5 (#224), Granite 3.1 8b Instruct: 35.2 (#236)

BenchmarkAmazon Nova MicroGranite 3.1 8b Instruct
LMArena Longer Query12061162

Writing & Preference Amazon Nova Micro leads

Amazon Nova Micro: 39.7 (#242), Granite 3.1 8b Instruct: 35.7 (#261)

BenchmarkAmazon Nova MicroGranite 3.1 8b Instruct
LMArena Text12081150
LMArena Creative Writing11721129
LMArena Multi-Turn11781108
WildBench74.3%—
LiveBench Language15.8%—

Frequently asked questions

Is Amazon Nova Micro better than Granite 3.1 8b Instruct?

Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 29.9 on the Noometry Index.

Is Amazon Nova Micro or Granite 3.1 8b Instruct better for coding?

Granite 3.1 8b Instruct scores higher on coding benchmarks: 33.9 versus 30.0 in the Noometry coding category.

How many benchmarks do Amazon Nova Micro and Granite 3.1 8b Instruct share?

13 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Granite 3.1 8b Instruct has 13.

Related comparisons

Go deeper