Model comparison

Amazon Nova Pro vs Gemini 1.0 Pro

Amazon Nova Pro is the stronger model overall, scoring 31.0 to 27.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

Amazon Nova Pro Amazon

31.0

Rank #281 Confirmed

Gemini 1.0 Pro Google

27.3

Rank #332 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Amazon Nova Pro scores higher in 8 categories and Gemini 1.0 Pro in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Amazon Nova Pro leads 28.5 to 9.3.

Side by side

Amazon Nova Pro and Gemini 1.0 Pro specifications
Amazon Nova ProGemini 1.0 Pro
ProviderAmazonGoogle
Noometry Index31.027.3
Released2024-12-032023-12-13
WeightsProprietaryProprietary
Context window300K—
Max output10K—
Input $ / M tokens$0.80—
Output $ / M tokens$3.20—
Results tracked3824

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

Category by category

Coding Amazon Nova Pro leads

Amazon Nova Pro: 35.1 (#229), Gemini 1.0 Pro: 32.2 (#275)

Coding benchmarks
BenchmarkAmazon Nova ProGemini 1.0 Pro
LMArena Coding12701108
LiveBench Coding38.1%—
HumanEval+—55.5%
MBPP+—61.4%

Agentic & Tool Use Not comparable

Amazon Nova Pro: 16.7 (#147), Gemini 1.0 Pro: —

Agentic & Tool Use benchmarks
BenchmarkAmazon Nova ProGemini 1.0 Pro
Berkeley Function Calling Leaderboard25%—
TheAgentCompany1.7%—

Reasoning Amazon Nova Pro leads

Amazon Nova Pro: 20.0 (#243), Gemini 1.0 Pro: 17.1 (#296)

Reasoning benchmarks
BenchmarkAmazon Nova ProGemini 1.0 Pro
LMArena Hard Prompts12461109
Epoch Capabilities Index123.8117.04
LiveBench Reasoning32.6%—
DTBench—45.9%
LiveBench Data Analysis48.3%—
LiveBench43.5%—

Math Amazon Nova Pro leads

Amazon Nova Pro: 28.5 (#243), Gemini 1.0 Pro: 9.3 (#321)

Math benchmarks
BenchmarkAmazon Nova ProGemini 1.0 Pro
LMArena Math12521132
OTIS Mock AIME 2024-2025—1.1%
Omni-MATH24.2%—
LiveBench Math38%—
MATH Level 5—11.2%

Knowledge Amazon Nova Pro leads

Amazon Nova Pro: 27.4 (#250), Gemini 1.0 Pro: 15.6 (#291)

Knowledge benchmarks
BenchmarkAmazon Nova ProGemini 1.0 Pro
LMArena Expert12111059
MMLU82%70%
GPQA Diamond—34%
Humanity's Last Exam4.4%—
MMLU-Pro67.3%—
Confabulations30.1%—
Vectara Hallucination Rate5.1%—
GPQA (HELM)44.6%—

Multimodal Not comparable

Amazon Nova Pro: 25.0 (#126), Gemini 1.0 Pro: —

Multimodal benchmarks
BenchmarkAmazon Nova ProGemini 1.0 Pro
LMArena Vision980—

Multilingual Amazon Nova Pro leads

Amazon Nova Pro: 39.7 (#223), Gemini 1.0 Pro: 33.4 (#252)

Multilingual benchmarks
BenchmarkAmazon Nova ProGemini 1.0 Pro
LMArena Non-English12341138
LMArena Chinese12441124
LMArena French12711145
LMArena German12431125
LMArena Japanese12001023
LMArena Russian12401186
LMArena Spanish11821119
LMArena Korean1203—

Instruction Following Amazon Nova Pro leads

Amazon Nova Pro: 64.9 (#226), Gemini 1.0 Pro: 57.6 (#267)

Instruction Following benchmarks
BenchmarkAmazon Nova ProGemini 1.0 Pro
LMArena Instruction Following12351114
LiveBench Instruction Following67.1%—
IFEval81.5%—

Long Context Amazon Nova Pro leads

Amazon Nova Pro: 38.1 (#205), Gemini 1.0 Pro: 34.3 (#249)

Long Context benchmarks
BenchmarkAmazon Nova ProGemini 1.0 Pro
LMArena Longer Query12551132

Writing & Preference Amazon Nova Pro leads

Amazon Nova Pro: 43.9 (#226), Gemini 1.0 Pro: 36.0 (#264)

Writing & Preference benchmarks
BenchmarkAmazon Nova ProGemini 1.0 Pro
LMArena Text12591149
LMArena Creative Writing12121131
LMArena Multi-Turn12461139
Short-Story Creative Writing60.5%—
WildBench77.7%—
LiveBench Language37%—

Frequently asked questions

Is Amazon Nova Pro better than Gemini 1.0 Pro?

Amazon Nova Pro is the stronger model overall, scoring 31.0 to 27.3 on the Noometry Index.

Is Amazon Nova Pro or Gemini 1.0 Pro better for coding?

Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 32.2 in the Noometry coding category.

How many benchmarks do Amazon Nova Pro and Gemini 1.0 Pro share?

18 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Gemini 1.0 Pro has 24.

Related comparisons

Go deeper