Noometry

Model comparison

Amazon Nova Micro vs C4ai Aya Expanse 32b

C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 30.4 on the Noometry Index.

Last verified . 18 shared benchmarks.

Amazon Nova Micro Amazon

30.4

Rank #294 Confirmed

C4ai Aya Expanse 32b Cohere

35.9

Rank #221 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Amazon Nova Micro scores higher in 0 categories and C4ai Aya Expanse 32b in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where C4ai Aya Expanse 32b leads 34.0 to 26.9.
  • The biggest single-benchmark swing is Vectara Hallucination Rate: 5.5% for Amazon Nova Micro and 10.9% for C4ai Aya Expanse 32b.
  • C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.

Side by side

Amazon Nova MicroC4ai Aya Expanse 32b
ProviderAmazonCohere
Noometry Index30.435.9
Released2024-12-032024-10-24
WeightsProprietaryOpen
Context window128K128K
Max output10K4K
Input $ / M tokens$0.035—
Output $ / M tokens$0.14—
Results tracked3218

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

Category by category

Coding C4ai Aya Expanse 32b leads

Amazon Nova Micro: 30.5 (#295), C4ai Aya Expanse 32b: 34.8 (#231)

BenchmarkAmazon Nova MicroC4ai Aya Expanse 32b
LMArena Coding12181197
LiveBench Coding20.2%—

Agentic & Tool Use Not comparable

Amazon Nova Micro: 22.1 (#132), C4ai Aya Expanse 32b: —

BenchmarkAmazon Nova MicroC4ai Aya Expanse 32b
Berkeley Function Calling Leaderboard22.3%—

Reasoning C4ai Aya Expanse 32b leads

Amazon Nova Micro: 17.4 (#294), C4ai Aya Expanse 32b: 23.3 (#180)

BenchmarkAmazon Nova MicroC4ai Aya Expanse 32b
LMArena Hard Prompts11911193
LiveBench Reasoning25.1%—
LiveBench Data Analysis34%—
LiveBench29.6%—

Math C4ai Aya Expanse 32b leads

Amazon Nova Micro: 26.9 (#254), C4ai Aya Expanse 32b: 34.0 (#197)

BenchmarkAmazon Nova MicroC4ai Aya Expanse 32b
LMArena Math12061200
Omni-MATH21.4%—
LiveBench Math34.5%—

Knowledge C4ai Aya Expanse 32b leads

Amazon Nova Micro: 29.6 (#237), C4ai Aya Expanse 32b: 33.2 (#206)

BenchmarkAmazon Nova MicroC4ai Aya Expanse 32b
Vectara Hallucination Rate5.5%10.9%
LMArena Expert11841182
MMLU-Pro51.1%—
GPQA (HELM)38.3%—
MMLU70.8%—

Multilingual C4ai Aya Expanse 32b leads

Amazon Nova Micro: 36.5 (#239), C4ai Aya Expanse 32b: 38.4 (#230)

BenchmarkAmazon Nova MicroC4ai Aya Expanse 32b
LMArena Non-English11861213
LMArena Chinese12091211
LMArena French12381248
LMArena German11921199
LMArena Japanese11541163
LMArena Korean11501158
LMArena Russian11851227
LMArena Spanish12251193

Instruction Following C4ai Aya Expanse 32b leads

Amazon Nova Micro: 56.3 (#272), C4ai Aya Expanse 32b: 62.6 (#237)

BenchmarkAmazon Nova MicroC4ai Aya Expanse 32b
LMArena Instruction Following11741196
LiveBench Instruction Following48%—
IFEval76%—

Long Context Too close to call

Amazon Nova Micro: 36.5 (#229), C4ai Aya Expanse 32b: 37.2 (#220)

BenchmarkAmazon Nova MicroC4ai Aya Expanse 32b
LMArena Longer Query12051228

Writing & Preference C4ai Aya Expanse 32b leads

Amazon Nova Micro: 39.5 (#247), C4ai Aya Expanse 32b: 42.2 (#235)

BenchmarkAmazon Nova MicroC4ai Aya Expanse 32b
LMArena Text12081224
LMArena Creative Writing11721200
LMArena Multi-Turn11781190
WildBench74.3%—
LiveBench Language15.8%—

Frequently asked questions

Is Amazon Nova Micro better than C4ai Aya Expanse 32b?

C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 30.4 on the Noometry Index.

Is Amazon Nova Micro or C4ai Aya Expanse 32b better for coding?

C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.8 versus 30.5 in the Noometry coding category.

Which has the bigger context window?

Both accept 128K tokens.

How many benchmarks do Amazon Nova Micro and C4ai Aya Expanse 32b share?

18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and C4ai Aya Expanse 32b has 18.

Related comparisons

Go deeper