Model comparison

Amazon Nova Pro vs Hunyuan Vision 1.5

Hunyuan Vision 1.5 is the stronger model overall, scoring 43.1 to 31.0 on the Noometry Index.

Last verified . 9 shared benchmarks.

Amazon Nova Pro Amazon

31.0

Rank #281 Confirmed

Hunyuan Vision 1.5 Tencent

43.1

Rank #98 Confirmed

Summary

  • They share 9 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Hunyuan Vision 1.5 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Hunyuan Vision 1.5 leads 60.1 to 43.9.

Side by side

Amazon Nova Pro and Hunyuan Vision 1.5 specifications
Amazon Nova ProHunyuan Vision 1.5
ProviderAmazonTencent
Noometry Index31.043.1
Released2024-12-03—
WeightsProprietaryProprietary
Context window300K—
Max output10K—
Input $ / M tokens$0.80—
Output $ / M tokens$3.20—
Results tracked389

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

Category by category

Coding Hunyuan Vision 1.5 leads

Amazon Nova Pro: 35.1 (#229), Hunyuan Vision 1.5: 41.8 (#119)

Coding benchmarks
BenchmarkAmazon Nova ProHunyuan Vision 1.5
LMArena Coding12701418
LiveBench Coding38.1%—

Agentic & Tool Use Not comparable

Amazon Nova Pro: 16.7 (#147), Hunyuan Vision 1.5: —

Agentic & Tool Use benchmarks
BenchmarkAmazon Nova ProHunyuan Vision 1.5
Berkeley Function Calling Leaderboard25%—
TheAgentCompany1.7%—

Reasoning Hunyuan Vision 1.5 leads

Amazon Nova Pro: 20.0 (#243), Hunyuan Vision 1.5: 28.9 (#97)

Reasoning benchmarks
BenchmarkAmazon Nova ProHunyuan Vision 1.5
LMArena Hard Prompts12461416
LiveBench Reasoning32.6%—
LiveBench Data Analysis48.3%—
Epoch Capabilities Index123.8—
LiveBench43.5%—

Math Not comparable

Amazon Nova Pro: 28.5 (#243), Hunyuan Vision 1.5: —

Math benchmarks
BenchmarkAmazon Nova ProHunyuan Vision 1.5
Omni-MATH24.2%—
LiveBench Math38%—
LMArena Math1252—

Knowledge Not comparable

Amazon Nova Pro: 27.4 (#250), Hunyuan Vision 1.5: —

Knowledge benchmarks
BenchmarkAmazon Nova ProHunyuan Vision 1.5
Humanity's Last Exam4.4%—
MMLU-Pro67.3%—
Confabulations30.1%—
Vectara Hallucination Rate5.1%—
GPQA (HELM)44.6%—
LMArena Expert1211—
MMLU82%—

Multimodal Hunyuan Vision 1.5 leads

Amazon Nova Pro: 25.0 (#126), Hunyuan Vision 1.5: 35.7 (#84)

Multimodal benchmarks
BenchmarkAmazon Nova ProHunyuan Vision 1.5
LMArena Vision9801180

Multilingual Hunyuan Vision 1.5 leads

Amazon Nova Pro: 39.7 (#223), Hunyuan Vision 1.5: 50.3 (#125)

Multilingual benchmarks
BenchmarkAmazon Nova ProHunyuan Vision 1.5
LMArena Non-English12341382
LMArena Chinese1244—
LMArena French1271—
LMArena German1243—
LMArena Japanese1200—
LMArena Korean1203—
LMArena Russian1240—
LMArena Spanish1182—

Instruction Following Hunyuan Vision 1.5 leads

Amazon Nova Pro: 64.9 (#226), Hunyuan Vision 1.5: 73.7 (#117)

Instruction Following benchmarks
BenchmarkAmazon Nova ProHunyuan Vision 1.5
LMArena Instruction Following12351397
LiveBench Instruction Following67.1%—
IFEval81.5%—

Long Context Hunyuan Vision 1.5 leads

Amazon Nova Pro: 38.1 (#205), Hunyuan Vision 1.5: 42.9 (#115)

Long Context benchmarks
BenchmarkAmazon Nova ProHunyuan Vision 1.5
LMArena Longer Query12551404

Writing & Preference Hunyuan Vision 1.5 leads

Amazon Nova Pro: 43.9 (#226), Hunyuan Vision 1.5: 60.1 (#100)

Writing & Preference benchmarks
BenchmarkAmazon Nova ProHunyuan Vision 1.5
LMArena Text12591405
LMArena Creative Writing12121388
LMArena Multi-Turn12461422
Short-Story Creative Writing60.5%—
WildBench77.7%—
LiveBench Language37%—

Frequently asked questions

Is Amazon Nova Pro better than Hunyuan Vision 1.5?

Hunyuan Vision 1.5 is the stronger model overall, scoring 43.1 to 31.0 on the Noometry Index.

Is Amazon Nova Pro or Hunyuan Vision 1.5 better for coding?

Hunyuan Vision 1.5 scores higher on coding benchmarks: 41.8 versus 35.1 in the Noometry coding category.

How many benchmarks do Amazon Nova Pro and Hunyuan Vision 1.5 share?

9 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Hunyuan Vision 1.5 has 9.

Related comparisons

Go deeper