Model comparison

Amazon Nova Pro vs Gemini 4 Argon

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 31.0 on the Noometry Index.

Last verified . 13 shared benchmarks.

Amazon Nova Pro Amazon

31.0

Rank #281 Confirmed

Gemini 4 Argon Google

56.5

Rank #24 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Gemini 4 Argon in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 4 Argon leads 73.9 to 28.5.

Side by side

Amazon Nova Pro and Gemini 4 Argon specifications
Amazon Nova ProGemini 4 Argon
ProviderAmazonGoogle
Noometry Index31.056.5
Released2024-12-032026-09-30
WeightsProprietaryProprietary
Context window300K—
Max output10K—
Input $ / M tokens$0.80—
Output $ / M tokens$3.20—
Results tracked3821

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

Category by category

Coding Gemini 4 Argon leads

Amazon Nova Pro: 35.1 (#229), Gemini 4 Argon: 62.0 (#9)

Coding benchmarks
BenchmarkAmazon Nova ProGemini 4 Argon
LMArena Coding12701550
LMArena WebDev—1678
FrontierSWE—55%
SciCode—61.8%
LiveBench Coding38.1%—

Agentic & Tool Use Gemini 4 Argon leads

Amazon Nova Pro: 16.7 (#147), Gemini 4 Argon: 49.2 (#8)

Agentic & Tool Use benchmarks
BenchmarkAmazon Nova ProGemini 4 Argon
APEX-Agents—82.2%
Berkeley Function Calling Leaderboard25%—
TheAgentCompany1.7%—
Vending-Bench 2—13,718

Reasoning Gemini 4 Argon leads

Amazon Nova Pro: 20.0 (#243), Gemini 4 Argon: 44.2 (#47)

Reasoning benchmarks
BenchmarkAmazon Nova ProGemini 4 Argon
LMArena Hard Prompts12461548
CritPt—27.1%
LiveBench Reasoning32.6%—
LiveBench Data Analysis48.3%—
Epoch Capabilities Index123.8—
LiveBench43.5%—

Math Gemini 4 Argon leads

Amazon Nova Pro: 28.5 (#243), Gemini 4 Argon: 73.9 (#17)

Math benchmarks
BenchmarkAmazon Nova ProGemini 4 Argon
LMArena Math12521536
ProofBench—99%
Omni-MATH24.2%—
LiveBench Math38%—

Knowledge Gemini 4 Argon leads

Amazon Nova Pro: 27.4 (#250), Gemini 4 Argon: 43.9 (#89)

Knowledge benchmarks
BenchmarkAmazon Nova ProGemini 4 Argon
LMArena Expert12111553
Humanity's Last Exam4.4%—
MMLU-Pro67.3%—
Confabulations30.1%—
Vectara Hallucination Rate5.1%—
GPQA (HELM)44.6%—
MMLU82%—

Multimodal Gemini 4 Argon leads

Amazon Nova Pro: 25.0 (#126), Gemini 4 Argon: 46.5 (#14)

Multimodal benchmarks
BenchmarkAmazon Nova ProGemini 4 Argon
LMArena Vision980—
Blueprint-Bench 2—54.4%

Multilingual Gemini 4 Argon leads

Amazon Nova Pro: 39.7 (#223), Gemini 4 Argon: 60.3 (#1)

Multilingual benchmarks
BenchmarkAmazon Nova ProGemini 4 Argon
LMArena Non-English12341523
LMArena Chinese12441610
LMArena Russian12401537
LMArena Spanish11821497
LMArena French1271—
LMArena German1243—
LMArena Japanese1200—
LMArena Korean1203—

Instruction Following Gemini 4 Argon leads

Amazon Nova Pro: 64.9 (#226), Gemini 4 Argon: 80.1 (#2)

Instruction Following benchmarks
BenchmarkAmazon Nova ProGemini 4 Argon
LMArena Instruction Following12351538
LiveBench Instruction Following67.1%—
IFEval81.5%—

Long Context Gemini 4 Argon leads

Amazon Nova Pro: 38.1 (#205), Gemini 4 Argon: 47.6 (#15)

Long Context benchmarks
BenchmarkAmazon Nova ProGemini 4 Argon
LMArena Longer Query12551549

Writing & Preference Gemini 4 Argon leads

Amazon Nova Pro: 43.9 (#226), Gemini 4 Argon: 71.4 (#19)

Writing & Preference benchmarks
BenchmarkAmazon Nova ProGemini 4 Argon
LMArena Text12591534
LMArena Creative Writing12121531
LMArena Multi-Turn12461557
Short-Story Creative Writing60.5%—
WildBench77.7%—
LiveBench Language37%—

Frequently asked questions

Is Amazon Nova Pro better than Gemini 4 Argon?

Gemini 4 Argon is the stronger model overall, scoring 56.5 to 31.0 on the Noometry Index.

Is Amazon Nova Pro or Gemini 4 Argon better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 35.1 in the Noometry coding category.

How many benchmarks do Amazon Nova Pro and Gemini 4 Argon share?

13 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Gemini 4 Argon has 21.

Related comparisons

Go deeper