Noometry

Model comparison

Claude Opus 4 vs Qwen3.5 35B-A3B

Claude Opus 4 is the stronger model overall, scoring 43.1 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 44× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.

Last verified . 24 shared benchmarks.

Claude Opus 4 Anthropic

43.1

Rank #100 Confirmed

Qwen3.5 35B-A3B Alibaba (Qwen)

42.0

Rank #123 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude Opus 4 scores higher in 5 categories and Qwen3.5 35B-A3B in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Claude Opus 4 leads 47.2 to 33.8.
  • The biggest single-benchmark swing is LMCA: 37.4% for Claude Opus 4 and 29.5% for Qwen3.5 35B-A3B.
  • Qwen3.5 35B-A3B is cheaper at $0.25 / $2 per million input/output tokens, against $15 / $75 for Claude Opus 4.
  • Qwen3.5 35B-A3B accepts more context: 262K tokens versus 200K.
  • Qwen3.5 35B-A3B has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4Qwen3.5 35B-A3B
ProviderAnthropicAlibaba (Qwen)
Noometry Index43.142.0
Released2025-05-222026-02-01
WeightsProprietaryOpen
Context window200K262K
Max output32K66K
Input $ / M tokens$15$0.25
Output $ / M tokens$75$2
Results tracked5628

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

Category by category

Coding Claude Opus 4 leads

Claude Opus 4: 47.2 (#62), Qwen3.5 35B-A3B: 33.8 (#251)

BenchmarkClaude Opus 4Qwen3.5 35B-A3B
LMArena Coding14421410
SWE-bench Verified70.7%—
SWE-bench Verified (bash only)67.6%—
Aider Polyglot72%—
LMArena WebDev—1254
SciCode—29.3%
GSO6.9%—
WeirdML43.7%—
AlgoTune1.33—

Agentic & Tool Use Not comparable

Claude Opus 4: 34.8 (#42), Qwen3.5 35B-A3B: —

BenchmarkClaude Opus 4Qwen3.5 35B-A3B
Cybench38%—
DeepResearch Bench46.8%—
LMArena Search1127—
METR Time Horizons63.9%—

Reasoning Claude Opus 4 leads

Claude Opus 4: 27.3 (#121), Qwen3.5 35B-A3B: 24.6 (#161)

BenchmarkClaude Opus 4Qwen3.5 35B-A3B
CritPt0.3%0.6%
LMArena Hard Prompts13991400
DTBench81.6%80%
LMCA37.4%29.5%
Epoch Capabilities Index142.67142.52
ARC-AGI-28.6%—
SimpleBench58.8%—
Kagi LLM Benchmark74.3%—
ARC-AGI-135.7%—
Chess Puzzles—10%
EnigmaEval5.6%—
ForecastBench61.1—

Math Claude Opus 4 leads

Claude Opus 4: 42.0 (#86), Qwen3.5 35B-A3B: 39.9 (#97)

BenchmarkClaude Opus 4Qwen3.5 35B-A3B
OTIS Mock AIME 2024-202564.4%70%
LMArena Math13901404
MathArena Final-Answer Competitions—56%
Omni-MATH61.6%—
MATH Level 585%—
FrontierMath (Feb 2025 set)4.5%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Qwen3.5 35B-A3B leads

Claude Opus 4: 44.0 (#88), Qwen3.5 35B-A3B: 47.8 (#79)

BenchmarkClaude Opus 4Qwen3.5 35B-A3B
GPQA Diamond76.3%83.5%
Vectara Hallucination Rate12%10.5%
LMArena Expert13861408
Humanity's Last Exam10.7%—
MMLU-Pro87.5%—
Confabulations15.9%—
GPQA (HELM)70.8%—

Multimodal Not comparable

Claude Opus 4: 31.5 (#106), Qwen3.5 35B-A3B: —

BenchmarkClaude Opus 4Qwen3.5 35B-A3B
LMArena Vision1192—
GeoBench49%—
VPCT38%—

Multilingual Qwen3.5 35B-A3B leads

Claude Opus 4: 48.8 (#138), Qwen3.5 35B-A3B: 50.0 (#127)

BenchmarkClaude Opus 4Qwen3.5 35B-A3B
LMArena Non-English13621378
LMArena Chinese13861457
LMArena French13721412
LMArena German13911367
LMArena Japanese13311325
LMArena Korean13211356
LMArena Russian13921376
LMArena Spanish13891392

Instruction Following Claude Opus 4 leads

Claude Opus 4: 77.1 (#28), Qwen3.5 35B-A3B: 72.8 (#128)

BenchmarkClaude Opus 4Qwen3.5 35B-A3B
LMArena Instruction Following14061379
IFEval91.8%—

Long Context Qwen3.5 35B-A3B leads

Claude Opus 4: 39.6 (#172), Qwen3.5 35B-A3B: 42.4 (#127)

BenchmarkClaude Opus 4Qwen3.5 35B-A3B
LMArena Longer Query14221389
Fiction.LiveBench61.1%—

Writing & Preference Claude Opus 4 leads

Claude Opus 4: 61.2 (#89), Qwen3.5 35B-A3B: 57.9 (#124)

BenchmarkClaude Opus 4Qwen3.5 35B-A3B
LMArena Text13771395
LMArena Creative Writing13871346
LMArena Multi-Turn13961390
Short-Story Creative Writing83.6%—
EQ-Bench Creative Writing1580—
WildBench85.2%—

Frequently asked questions

Is Claude Opus 4 better than Qwen3.5 35B-A3B?

Claude Opus 4 is the stronger model overall, scoring 43.1 to 42.0 on the Noometry Index. Qwen3.5 35B-A3B costs 44× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4 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; Claude Opus 4 lists at $15 and $75.

Is Claude Opus 4 or Qwen3.5 35B-A3B better for coding?

Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

Qwen3.5 35B-A3B does, with 262K tokens against 200K.

How many benchmarks do Claude Opus 4 and Qwen3.5 35B-A3B share?

24 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Qwen3.5 35B-A3B has 28.

Related comparisons

Go deeper