Noometry

Model comparison

Amazon Nova Pro vs Claude Sonnet 4.6

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 31.0 on the Noometry Index. Amazon Nova Pro costs 4.3× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Last verified . 20 shared benchmarks.

Amazon Nova Pro Amazon

31.0

Rank #281 Confirmed

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and Claude Sonnet 4.6 in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Claude Sonnet 4.6 leads 70.2 to 43.9.
  • The biggest single-benchmark swing is Vectara Hallucination Rate: 5.1% for Amazon Nova Pro and 10.6% for Claude Sonnet 4.6.
  • Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
  • Claude Sonnet 4.6 accepts more context: 1M tokens versus 300K.

Side by side

Amazon Nova ProClaude Sonnet 4.6
ProviderAmazonAnthropic
Noometry Index31.050.3
Released2024-12-032026-02-17
WeightsProprietaryProprietary
Context window300K1M
Max output10K128K
Input $ / M tokens$0.80$3
Output $ / M tokens$3.20$15
Results tracked3857

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

Category by category

Coding Claude Sonnet 4.6 leads

Amazon Nova Pro: 35.1 (#229), Claude Sonnet 4.6: 46.3 (#67)

BenchmarkAmazon Nova ProClaude Sonnet 4.6
LMArena Coding12701504
SWE-bench Verified—75.2%
DeepSWE—29.9%
FrontierCode—24.3%
LMArena WebDev—1522
SciCode—46.8%
WeirdML—66.1%
LiveBench Coding38.1%—
ALE-Bench—1,327

Agentic & Tool Use Claude Sonnet 4.6 leads

Amazon Nova Pro: 16.7 (#147), Claude Sonnet 4.6: 39.1 (#28)

BenchmarkAmazon Nova ProClaude Sonnet 4.6
Terminal-Bench—53.4%
APEX-Agents—43%
Berkeley Function Calling Leaderboard25%—
OSWorld 2.0—9.3%
TheAgentCompany1.7%—
DeepResearch Bench—54.9%
OSWorld—72.1%
ExploitBench—23.6%
GBAEval—48.8%
GDP.pdf—18%
LMArena Search—1221
Vending-Bench 2—7,204

Reasoning Claude Sonnet 4.6 leads

Amazon Nova Pro: 20.0 (#243), Claude Sonnet 4.6: 46.1 (#45)

BenchmarkAmazon Nova ProClaude Sonnet 4.6
LMArena Hard Prompts12461484
Epoch Capabilities Index123.8152.24
ARC-AGI-2—60.4%
NYT Connections (extended)—80.9%
ARC-AGI-1—86.5%
CritPt—3.1%
Chess Puzzles—13%
Thematic Generalization—76.3%
LiveBench Reasoning32.6%—
Mystery Game Puzzles—16%
DTBench—89.9%
LiveBench Data Analysis48.3%—
LMCA—46.5%
ForecastBench—62
LiveBench43.5%—

Math Claude Sonnet 4.6 leads

Amazon Nova Pro: 28.5 (#243), Claude Sonnet 4.6: 52.9 (#49)

BenchmarkAmazon Nova ProClaude Sonnet 4.6
LMArena Math12521462
OTIS Mock AIME 2024-2025—85.8%
ProofBench—45%
Omni-MATH24.2%—
LiveBench Math38%—
FrontierMath (Feb 2025 set)—32.4%
FrontierMath Tier 4 (v1)—8.3%

Knowledge Claude Sonnet 4.6 leads

Amazon Nova Pro: 27.4 (#250), Claude Sonnet 4.6: 51.7 (#65)

BenchmarkAmazon Nova ProClaude Sonnet 4.6
Vectara Hallucination Rate5.1%10.6%
LMArena Expert12111500
GPQA Diamond—87.4%
Humanity's Last Exam4.4%—
SimpleQA Verified—35.5%
MMLU-Pro67.3%—
Confabulations30.1%—
GPQA (HELM)44.6%—
MMLU82%—

Multimodal Claude Sonnet 4.6 leads

Amazon Nova Pro: 25.0 (#126), Claude Sonnet 4.6: 38.0 (#68)

BenchmarkAmazon Nova ProClaude Sonnet 4.6
LMArena Vision9801283
Blueprint-Bench 2—6.7%
LMArena Document—1482

Multilingual Claude Sonnet 4.6 leads

Amazon Nova Pro: 39.7 (#223), Claude Sonnet 4.6: 54.4 (#41)

BenchmarkAmazon Nova ProClaude Sonnet 4.6
LMArena Non-English12341440
LMArena Chinese12441491
LMArena French12711465
LMArena German12431428
LMArena Japanese12001420
LMArena Korean12031411
LMArena Russian12401440
LMArena Spanish11821464

Instruction Following Claude Sonnet 4.6 leads

Amazon Nova Pro: 64.9 (#226), Claude Sonnet 4.6: 77.4 (#25)

BenchmarkAmazon Nova ProClaude Sonnet 4.6
LMArena Instruction Following12351475
LiveBench Instruction Following67.1%—
IFEval81.5%—

Long Context Claude Sonnet 4.6 leads

Amazon Nova Pro: 38.1 (#205), Claude Sonnet 4.6: 45.3 (#44)

BenchmarkAmazon Nova ProClaude Sonnet 4.6
LMArena Longer Query12551479

Writing & Preference Claude Sonnet 4.6 leads

Amazon Nova Pro: 43.9 (#226), Claude Sonnet 4.6: 70.2 (#22)

BenchmarkAmazon Nova ProClaude Sonnet 4.6
LMArena Text12591458
LMArena Creative Writing12121435
LMArena Multi-Turn12461464
Short-Story Creative Writing60.5%—
EQ-Bench Creative Writing—1810
WildBench77.7%—
EQ-Bench 4—1207
LiveBench Language37%—

Frequently asked questions

Is Amazon Nova Pro better than Claude Sonnet 4.6?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 31.0 on the Noometry Index. Amazon Nova Pro costs 4.3× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Which is cheaper, Amazon Nova Pro or Claude Sonnet 4.6?

Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

Is Amazon Nova Pro or Claude Sonnet 4.6 better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 35.1 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 300K.

How many benchmarks do Amazon Nova Pro and Claude Sonnet 4.6 share?

20 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Claude Sonnet 4.6 has 57.

Related comparisons

Go deeper