Noometry

Model comparison

Nova 2 Lite vs Qwen3.5 35B-A3B

Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 39.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

Nova 2 Lite Amazon

39.0

Rank #161 Confirmed

Qwen3.5 35B-A3B Alibaba (Qwen)

41.7

Rank #118 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Nova 2 Lite scores higher in 2 categories and Qwen3.5 35B-A3B in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Nova 2 Lite leads 40.1 to 33.5.
  • The biggest single-benchmark swing is Vectara Hallucination Rate: 5.1% for Nova 2 Lite and 10.5% for Qwen3.5 35B-A3B.
  • Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
  • Nova 2 Lite accepts more context: 1M tokens versus 262K.
  • Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.

Side by side

Nova 2 LiteQwen3.5 35B-A3B
ProviderAmazonAlibaba (Qwen)
Noometry Index39.041.7
Released2025-12-012026-02-01
WeightsProprietaryOpen
Context window1M262K
Max output64K66K
Input $ / M tokens$0.30$0.25
Output $ / M tokens$2.50$2
Results tracked1928

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

Category by category

Coding Nova 2 Lite leads

Nova 2 Lite: 40.1 (#131), Qwen3.5 35B-A3B: 33.5 (#244)

BenchmarkNova 2 LiteQwen3.5 35B-A3B
LMArena Coding13861410
LMArena WebDev—1254
SciCode—29.3%

Agentic & Tool Use Not comparable

Nova 2 Lite: 23.9 (#114), Qwen3.5 35B-A3B: —

BenchmarkNova 2 LiteQwen3.5 35B-A3B
Berkeley Function Calling Leaderboard27.1%—

Reasoning Nova 2 Lite leads

Nova 2 Lite: 26.4 (#120), Qwen3.5 35B-A3B: 23.9 (#158)

BenchmarkNova 2 LiteQwen3.5 35B-A3B
LMArena Hard Prompts13641400
CritPt—0.6%
Chess Puzzles—10%
DTBench—80%
LMCA—29.5%
Epoch Capabilities Index—142.52

Math Qwen3.5 35B-A3B leads

Nova 2 Lite: 34.8 (#154), Qwen3.5 35B-A3B: 38.4 (#86)

BenchmarkNova 2 LiteQwen3.5 35B-A3B
LMArena Math13591404
MathArena Final-Answer Competitions—56%
OTIS Mock AIME 2024-2025—70%

Knowledge Qwen3.5 35B-A3B leads

Nova 2 Lite: 42.5 (#88), Qwen3.5 35B-A3B: 47.7 (#73)

BenchmarkNova 2 LiteQwen3.5 35B-A3B
Vectara Hallucination Rate5.1%10.5%
LMArena Expert13601408
GPQA Diamond—83.5%

Multilingual Qwen3.5 35B-A3B leads

Nova 2 Lite: 47.3 (#148), Qwen3.5 35B-A3B: 50.2 (#122)

BenchmarkNova 2 LiteQwen3.5 35B-A3B
LMArena Non-English13371379
LMArena Chinese13641458
LMArena French13811412
LMArena German13431367
LMArena Japanese12731326
LMArena Korean12841354
LMArena Russian13431377
LMArena Spanish13721390

Instruction Following Qwen3.5 35B-A3B leads

Nova 2 Lite: 70.7 (#156), Qwen3.5 35B-A3B: 73.0 (#123)

BenchmarkNova 2 LiteQwen3.5 35B-A3B
LMArena Instruction Following13351379

Long Context Qwen3.5 35B-A3B leads

Nova 2 Lite: 40.6 (#145), Qwen3.5 35B-A3B: 42.4 (#122)

BenchmarkNova 2 LiteQwen3.5 35B-A3B
LMArena Longer Query13351390

Writing & Preference Qwen3.5 35B-A3B leads

Nova 2 Lite: 54.1 (#150), Qwen3.5 35B-A3B: 58.1 (#118)

BenchmarkNova 2 LiteQwen3.5 35B-A3B
LMArena Text13621395
LMArena Creative Writing12911347
LMArena Multi-Turn13381391

Frequently asked questions

Is Nova 2 Lite better than Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 39.0 on the Noometry Index.

Which is cheaper, Nova 2 Lite 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; Nova 2 Lite lists at $0.30 and $2.50.

Is Nova 2 Lite or Qwen3.5 35B-A3B better for coding?

Nova 2 Lite scores higher on coding benchmarks: 40.1 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

Nova 2 Lite does, with 1M tokens against 262K.

How many benchmarks do Nova 2 Lite and Qwen3.5 35B-A3B share?

18 benchmarks have published results for both models. Nova 2 Lite has 19 scored results on Noometry and Qwen3.5 35B-A3B has 28.

Related comparisons

Go deeper