Noometry

Model comparison

Amazon Nova Pro vs GPT-5.4

GPT-5.4 is the stronger model overall, scoring 59.4 to 31.0 on the Noometry Index. Amazon Nova Pro costs 4.0× less per token, which makes it the better buy when GPT-5.4's lead doesn't matter for your workload.

Last verified . 21 shared benchmarks.

Amazon Nova Pro Amazon

31.0

Rank #281 Confirmed

GPT-5.4 OpenAI

59.4

Rank #16 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and GPT-5.4 in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.4 leads 73.5 to 28.5.
  • The biggest single-benchmark swing is Humanity's Last Exam: 4.4% for Amazon Nova Pro and 36.2% for GPT-5.4.
  • Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $2.50 / $15 for GPT-5.4.
  • GPT-5.4 accepts more context: 1.05M tokens versus 300K.

Side by side

Amazon Nova ProGPT-5.4
ProviderAmazonOpenAI
Noometry Index31.059.4
Released2024-12-032026-03-05
WeightsProprietaryProprietary
Context window300K1.05M
Max output10K128K
Input $ / M tokens$0.80$2.50
Output $ / M tokens$3.20$15
Results tracked3868

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

Category by category

Coding GPT-5.4 leads

Amazon Nova Pro: 35.1 (#229), GPT-5.4: 52.6 (#33)

BenchmarkAmazon Nova ProGPT-5.4
LMArena Coding12701497
SWE-bench Verified—76.9%
DeepSWE—51.8%
LMArena WebDev—1465
SciCode—56.6%
GSO—31.4%
WeirdML—77.7%
LiveBench Coding38.1%—
MirrorCode—15.6%
ALE-Bench—1,607
AlgoTune—1.85

Agentic & Tool Use GPT-5.4 leads

Amazon Nova Pro: 16.7 (#147), GPT-5.4: 46.5 (#13)

BenchmarkAmazon Nova ProGPT-5.4
Terminal-Bench—81.8%
APEX-Agents—52.4%
Berkeley Function Calling Leaderboard25%—
TheAgentCompany1.7%—
τ²-bench Banking—39.4%
DeepResearch Bench—35.1%
PostTrainBench—19%
GBAEval—45.1%
LMArena Search—1197
METR Time Horizons—74.3%
Vending-Bench 2—6,144

Reasoning GPT-5.4 leads

Amazon Nova Pro: 20.0 (#243), GPT-5.4: 61.8 (#19)

BenchmarkAmazon Nova ProGPT-5.4
LMArena Hard Prompts12461485
Epoch Capabilities Index123.8156.81
ARC-AGI-2—74%
Kagi LLM Benchmark—63.8%
NYT Connections (extended)—91.3%
ARC-AGI-1—93.7%
CritPt—23.4%
Chess Puzzles—44%
EnigmaEval—16%
Thematic Generalization—80%
EBR-Bench—25.4%
LiveBench Reasoning32.6%—
Mystery Game Puzzles—37%
DTBench—94.4%
LiveBench Data Analysis48.3%—
LMCA—52%
ForecastBench—59.5
LiveBench43.5%—

Math GPT-5.4 leads

Amazon Nova Pro: 28.5 (#243), GPT-5.4: 73.5 (#19)

BenchmarkAmazon Nova ProGPT-5.4
LMArena Math12521488
FrontierMath (Tiers 1-3)—78.6%
FrontierMath Tier 4—49%
MathArena Final-Answer Competitions—83.1%
OTIS Mock AIME 2024-2025—97.8%
ProofBench—56%
Omni-MATH24.2%—
LiveBench Math38%—
FrontierMath (Feb 2025 set)—47.6%
FrontierMath Tier 4 (v1)—27.1%

Knowledge GPT-5.4 leads

Amazon Nova Pro: 27.4 (#250), GPT-5.4: 65.3 (#14)

BenchmarkAmazon Nova ProGPT-5.4
Humanity's Last Exam4.4%36.2%
Vectara Hallucination Rate5.1%7%
LMArena Expert12111507
GPQA Diamond—93.3%
SimpleQA Verified—45.1%
MMLU-Pro67.3%—
Confabulations30.1%—
GPQA (HELM)44.6%—
MMLU82%—

Multimodal GPT-5.4 leads

Amazon Nova Pro: 25.0 (#126), GPT-5.4: 43.7 (#20)

BenchmarkAmazon Nova ProGPT-5.4
LMArena Vision9801303
Blueprint-Bench 2—27.1%
Furniture Assembly—37.5%
LMArena Document—1471

Multilingual GPT-5.4 leads

Amazon Nova Pro: 39.7 (#223), GPT-5.4: 56.2 (#23)

BenchmarkAmazon Nova ProGPT-5.4
LMArena Non-English12341465
LMArena Chinese12441519
LMArena French12711493
LMArena German12431472
LMArena Japanese12001485
LMArena Korean12031448
LMArena Russian12401480
LMArena Spanish11821454

Instruction Following GPT-5.4 leads

Amazon Nova Pro: 64.9 (#226), GPT-5.4: 77.1 (#27)

BenchmarkAmazon Nova ProGPT-5.4
LMArena Instruction Following12351469
LiveBench Instruction Following67.1%—
IFEval81.5%—

Long Context GPT-5.4 leads

Amazon Nova Pro: 38.1 (#205), GPT-5.4: 50.3 (#8)

BenchmarkAmazon Nova ProGPT-5.4
LMArena Longer Query12551473
CL-bench—27.9%
CL-bench Life—21.7%

Writing & Preference GPT-5.4 leads

Amazon Nova Pro: 43.9 (#226), GPT-5.4: 71.9 (#17)

BenchmarkAmazon Nova ProGPT-5.4
LMArena Text12591469
LMArena Creative Writing12121439
LMArena Multi-Turn12461482
Short-Story Creative Writing60.5%—
EQ-Bench Creative Writing—1840
WildBench77.7%—
EQ-Bench 4—1272
LiveBench Language37%—

Frequently asked questions

Is Amazon Nova Pro better than GPT-5.4?

GPT-5.4 is the stronger model overall, scoring 59.4 to 31.0 on the Noometry Index. Amazon Nova Pro costs 4.0× less per token, which makes it the better buy when GPT-5.4's lead doesn't matter for your workload.

Which is cheaper, Amazon Nova Pro or GPT-5.4?

Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; GPT-5.4 lists at $2.50 and $15.

Is Amazon Nova Pro or GPT-5.4 better for coding?

GPT-5.4 scores higher on coding benchmarks: 52.6 versus 35.1 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 does, with 1.05M tokens against 300K.

How many benchmarks do Amazon Nova Pro and GPT-5.4 share?

21 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-5.4 has 68.

Related comparisons

Go deeper