Noometry

Model comparison

Amazon Nova Micro vs GPT-4.5

GPT-4.5 is the stronger model overall, scoring 37.2 to 30.4 on the Noometry Index.

Last verified . 23 shared benchmarks.

Amazon Nova Micro Amazon

30.4

Rank #294 Confirmed

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Amazon Nova Micro scores higher in 1 category and GPT-4.5 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-4.5 leads 56.9 to 39.5.
  • The biggest single-benchmark swing is LiveBench Coding: 20.2% for Amazon Nova Micro and 75.2% for GPT-4.5.

Side by side

Amazon Nova MicroGPT-4.5
ProviderAmazonOpenAI
Noometry Index30.437.2
Released2024-12-032025-02-27
WeightsProprietaryProprietary
Context window128K—
Max output10K—
Input $ / M tokens$0.035—
Output $ / M tokens$0.14—
Results tracked3242

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

Category by category

Coding GPT-4.5 leads

Amazon Nova Micro: 30.5 (#295), GPT-4.5: 42.2 (#109)

BenchmarkAmazon Nova MicroGPT-4.5
LiveBench Coding20.2%75.2%
LMArena Coding12181396
Aider Polyglot—44.9%
WeirdML—39.4%

Agentic & Tool Use GPT-4.5 leads

Amazon Nova Micro: 22.1 (#132), GPT-4.5: 27.9 (#97)

BenchmarkAmazon Nova MicroGPT-4.5
Berkeley Function Calling Leaderboard22.3%—
Cybench—17.5%

Reasoning Amazon Nova Micro leads

Amazon Nova Micro: 17.4 (#294), GPT-4.5: 13.9 (#330)

BenchmarkAmazon Nova MicroGPT-4.5
LiveBench Reasoning25.1%71.1%
LMArena Hard Prompts11911403
LiveBench Data Analysis34%64.3%
LiveBench29.6%69%
ARC-AGI-2—0.8%
SimpleBench—34.5%
ARC-AGI-1—10.3%
EnigmaEval—3.2%
Epoch Capabilities Index—136.74
ForecastBench—61.7

Math GPT-4.5 leads

Amazon Nova Micro: 26.9 (#254), GPT-4.5: 32.6 (#211)

BenchmarkAmazon Nova MicroGPT-4.5
LiveBench Math34.5%69.3%
LMArena Math12061412
OTIS Mock AIME 2024-2025—37.8%
Omni-MATH21.4%—
MATH Level 5—78.6%

Knowledge GPT-4.5 leads

Amazon Nova Micro: 29.6 (#237), GPT-4.5: 32.5 (#211)

BenchmarkAmazon Nova MicroGPT-4.5
LMArena Expert11841394
GPQA Diamond—68.7%
Humanity's Last Exam—5.4%
MMLU-Pro51.1%—
Confabulations—13.6%
Vectara Hallucination Rate5.5%—
GPQA (HELM)38.3%—
MMLU70.8%—

Multimodal Not comparable

Amazon Nova Micro: —, GPT-4.5: 37.6 (#71)

BenchmarkAmazon Nova MicroGPT-4.5
LMArena Vision—1195
VPCT—45%

Multilingual GPT-4.5 leads

Amazon Nova Micro: 36.5 (#239), GPT-4.5: 52.5 (#83)

BenchmarkAmazon Nova MicroGPT-4.5
LMArena Non-English11861413
LMArena Chinese12091421
LMArena French12381418
LMArena German11921457
LMArena Japanese11541416
LMArena Korean11501392
LMArena Russian11851419
LMArena Spanish1225—

Instruction Following GPT-4.5 leads

Amazon Nova Micro: 56.3 (#272), GPT-4.5: 72.6 (#134)

BenchmarkAmazon Nova MicroGPT-4.5
LiveBench Instruction Following48%72.3%
LMArena Instruction Following11741404
IFEval76%—

Long Context GPT-4.5 leads

Amazon Nova Micro: 36.5 (#229), GPT-4.5: 40.4 (#155)

BenchmarkAmazon Nova MicroGPT-4.5
LMArena Longer Query12051406
Fiction.LiveBench—63.9%

Writing & Preference GPT-4.5 leads

Amazon Nova Micro: 39.5 (#247), GPT-4.5: 56.9 (#134)

BenchmarkAmazon Nova MicroGPT-4.5
LMArena Text12081417
LMArena Creative Writing11721394
LMArena Multi-Turn11781444
LiveBench Language15.8%61.5%
Short-Story Creative Writing—75.6%
EQ-Bench Creative Writing—1258
WildBench74.3%—

Frequently asked questions

Is Amazon Nova Micro better than GPT-4.5?

GPT-4.5 is the stronger model overall, scoring 37.2 to 30.4 on the Noometry Index.

Is Amazon Nova Micro or GPT-4.5 better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 30.5 in the Noometry coding category.

How many benchmarks do Amazon Nova Micro and GPT-4.5 share?

23 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and GPT-4.5 has 42.

Related comparisons

Go deeper