Noometry

Model comparison

Amazon Nova Pro vs Qwen3.5 35B-A3B

Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 30.5 on the Noometry Index.

Last verified . 19 shared benchmarks.

Amazon Nova Pro Amazon

30.5

Rank #278 Confirmed

Qwen3.5 35B-A3B Alibaba (Qwen)

41.7

Rank #118 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 1 category and Qwen3.5 35B-A3B in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.7 to 27.1.
  • The biggest single-benchmark swing is Vectara Hallucination Rate: 5.1% for Amazon Nova Pro and 10.5% for Qwen3.5 35B-A3B.
  • Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
  • Amazon Nova Pro accepts more context: 300K tokens versus 262K.
  • Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.

Side by side

Amazon Nova ProQwen3.5 35B-A3B
ProviderAmazonAlibaba (Qwen)
Noometry Index30.541.7
Released2024-12-032026-02-01
WeightsProprietaryOpen
Context window300K262K
Max output10K66K
Input $ / M tokens$0.80$0.25
Output $ / M tokens$3.20$2
Results tracked3828

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

Category by category

Coding Amazon Nova Pro leads

Amazon Nova Pro: 34.6 (#224), Qwen3.5 35B-A3B: 33.5 (#244)

BenchmarkAmazon Nova ProQwen3.5 35B-A3B
LMArena Coding12701410
LMArena WebDev—1254
SciCode—29.3%
LiveBench Coding38.1%—

Agentic & Tool Use Not comparable

Amazon Nova Pro: 16.6 (#139), Qwen3.5 35B-A3B: —

BenchmarkAmazon Nova ProQwen3.5 35B-A3B
Berkeley Function Calling Leaderboard25%—
TheAgentCompany1.7%—

Reasoning Qwen3.5 35B-A3B leads

Amazon Nova Pro: 19.2 (#240), Qwen3.5 35B-A3B: 23.9 (#158)

BenchmarkAmazon Nova ProQwen3.5 35B-A3B
LMArena Hard Prompts12461400
Epoch Capabilities Index123.75142.52
CritPt—0.6%
Chess Puzzles—10%
LiveBench Reasoning32.6%—
DTBench—80%
LiveBench Data Analysis48.3%—
LMCA—29.5%
LiveBench43.5%—

Math Qwen3.5 35B-A3B leads

Amazon Nova Pro: 26.4 (#240), Qwen3.5 35B-A3B: 38.4 (#86)

BenchmarkAmazon Nova ProQwen3.5 35B-A3B
LMArena Math12521404
MathArena Final-Answer Competitions—56%
OTIS Mock AIME 2024-2025—70%
Omni-MATH24.2%—
LiveBench Math38%—

Knowledge Qwen3.5 35B-A3B leads

Amazon Nova Pro: 27.1 (#246), Qwen3.5 35B-A3B: 47.7 (#73)

BenchmarkAmazon Nova ProQwen3.5 35B-A3B
Vectara Hallucination Rate5.1%10.5%
LMArena Expert12111408
GPQA Diamond—83.5%
Humanity's Last Exam4.4%—
MMLU-Pro67.3%—
Confabulations30.1%—
GPQA (HELM)44.6%—
MMLU82%—

Multimodal Not comparable

Amazon Nova Pro: 24.5 (#121), Qwen3.5 35B-A3B: —

BenchmarkAmazon Nova ProQwen3.5 35B-A3B
LMArena Vision980—

Multilingual Qwen3.5 35B-A3B leads

Amazon Nova Pro: 39.9 (#218), Qwen3.5 35B-A3B: 50.2 (#122)

BenchmarkAmazon Nova ProQwen3.5 35B-A3B
LMArena Non-English12341379
LMArena Chinese12441458
LMArena French12701412
LMArena German12431367
LMArena Japanese12001326
LMArena Korean12031354
LMArena Russian12401377
LMArena Spanish11821390

Instruction Following Qwen3.5 35B-A3B leads

Amazon Nova Pro: 65.1 (#221), Qwen3.5 35B-A3B: 73.0 (#123)

BenchmarkAmazon Nova ProQwen3.5 35B-A3B
LMArena Instruction Following12351379
LiveBench Instruction Following67.1%—
IFEval81.5%—

Long Context Qwen3.5 35B-A3B leads

Amazon Nova Pro: 38.1 (#199), Qwen3.5 35B-A3B: 42.4 (#122)

BenchmarkAmazon Nova ProQwen3.5 35B-A3B
LMArena Longer Query12551390

Writing & Preference Qwen3.5 35B-A3B leads

Amazon Nova Pro: 44.1 (#221), Qwen3.5 35B-A3B: 58.1 (#118)

BenchmarkAmazon Nova ProQwen3.5 35B-A3B
LMArena Text12591395
LMArena Creative Writing12121347
LMArena Multi-Turn12451391
Short-Story Creative Writing60.5%—
WildBench77.7%—
LiveBench Language37%—

Frequently asked questions

Is Amazon Nova Pro better than Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 30.5 on the Noometry Index.

Which is cheaper, Amazon Nova Pro or Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.

Is Amazon Nova Pro or Qwen3.5 35B-A3B better for coding?

Amazon Nova Pro scores higher on coding benchmarks: 34.6 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

Amazon Nova Pro does, with 300K tokens against 262K.

How many benchmarks do Amazon Nova Pro and Qwen3.5 35B-A3B share?

19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Qwen3.5 35B-A3B has 28.

Related comparisons

Go deeper