Noometry

Model comparison

Claude Opus 4.6 vs Qwen3.5 122B-A10B

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 42.1 on the Noometry Index. Qwen3.5 122B-A10B costs 9.1× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 25 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

Qwen3.5 122B-A10B Alibaba (Qwen)

42.1

Rank #119 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude Opus 4.6 scores higher in 8 categories and Qwen3.5 122B-A10B in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.6 leads 57.8 to 27.2.
  • The biggest single-benchmark swing is NYT Connections (extended): 92.1% for Claude Opus 4.6 and 51.7% for Qwen3.5 122B-A10B.
  • Qwen3.5 122B-A10B is cheaper at $0.40 / $3.20 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
  • Claude Opus 4.6 accepts more context: 1M tokens versus 262K.
  • Qwen3.5 122B-A10B has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.6Qwen3.5 122B-A10B
ProviderAnthropicAlibaba (Qwen)
Noometry Index58.242.1
Released2026-02-042026-02-23
WeightsProprietaryOpen
Context window1M262K
Max output128K66K
Input $ / M tokens$5$0.40
Output $ / M tokens$25$3.20
Results tracked6827

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

Category by category

Coding Claude Opus 4.6 leads

Claude Opus 4.6: 57.2 (#20), Qwen3.5 122B-A10B: 39.1 (#162)

BenchmarkClaude Opus 4.6Qwen3.5 122B-A10B
LMArena WebDev15471360
LMArena Coding15361436
SWE-bench Verified78.7%—
FrontierCode26.6%—
SWE-bench Verified (bash only)75.6%—
SWE-bench Multilingual72%—
SciCode—35.6%
GSO41.2%—
WeirdML78%—
ALE-Bench996.5—
AlgoTune1.47—

Agentic & Tool Use Not comparable

Claude Opus 4.6: 51.1 (#4), Qwen3.5 122B-A10B: —

BenchmarkClaude Opus 4.6Qwen3.5 122B-A10B
Terminal-Bench79.8%—
APEX-Agents46.3%—
Remote Labor Index4.2%—
τ²-bench Banking27.3%—
Cybench93%—
DeepResearch Bench55.3%—
GBAEval44.1%—
LMArena Search1253—
METR Time Horizons78.9%—
Vending-Bench 28,018—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.8 (#23), Qwen3.5 122B-A10B: 27.2 (#123)

BenchmarkClaude Opus 4.6Qwen3.5 122B-A10B
NYT Connections (extended)92.1%51.7%
Thematic Generalization80.6%51.2%
LMArena Hard Prompts15271421
Mystery Game Puzzles25%17%
DTBench91.2%84.3%
LMCA55.8%32.2%
ARC-AGI-269.2%—
SimpleBench67.6%—
Kagi LLM Benchmark83.6%—
ARC-AGI-194%—
CritPt—0.9%
Chess Puzzles17%—
EnigmaEval7.6%—
EBR-Bench12.7%—
Epoch Capabilities Index155.24—
ForecastBench60—

Math Claude Opus 4.6 leads

Claude Opus 4.6: 63.0 (#31), Qwen3.5 122B-A10B: 39.1 (#112)

BenchmarkClaude Opus 4.6Qwen3.5 122B-A10B
LMArena Math15191432
FrontierMath (Tiers 1-3)66%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions78.5%—
OTIS Mock AIME 2024-202594.4%—
ProofBench50%—
FrontierMath (Feb 2025 set)40.7%—
FrontierMath Tier 4 (v1)22.9%—

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.9 (#26), Qwen3.5 122B-A10B: 38.8 (#142)

BenchmarkClaude Opus 4.6Qwen3.5 122B-A10B
Vectara Hallucination Rate12.2%11.2%
LMArena Expert15461432
GPQA Diamond90.5%—
Humanity's Last Exam34.4%—
SimpleQA Verified47%—

Multimodal Qwen3.5 122B-A10B leads

Claude Opus 4.6: 37.3 (#74), Qwen3.5 122B-A10B: 39.6 (#57)

BenchmarkClaude Opus 4.6Qwen3.5 122B-A10B
LMArena Vision13161245
Furniture Assembly28.3%—
LMArena Document1507—

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 57.9 (#6), Qwen3.5 122B-A10B: 51.6 (#107)

BenchmarkClaude Opus 4.6Qwen3.5 122B-A10B
LMArena Non-English14891400
LMArena Chinese15511462
LMArena French15131442
LMArena German15021426
LMArena Japanese14841367
LMArena Korean14641352
LMArena Russian14971400
LMArena Spanish15101424

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), Qwen3.5 122B-A10B: 73.8 (#115)

BenchmarkClaude Opus 4.6Qwen3.5 122B-A10B
LMArena Instruction Following15231399

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), Qwen3.5 122B-A10B: 43.0 (#109)

BenchmarkClaude Opus 4.6Qwen3.5 122B-A10B
LMArena Longer Query15201410
CL-bench20.7%—
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.5 (#10), Qwen3.5 122B-A10B: 60.0 (#105)

BenchmarkClaude Opus 4.6Qwen3.5 122B-A10B
LMArena Text15031417
LMArena Creative Writing15051368
LMArena Multi-Turn15131416
EQ-Bench Creative Writing1809—
EQ-Bench 41223—

Frequently asked questions

Is Claude Opus 4.6 better than Qwen3.5 122B-A10B?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 42.1 on the Noometry Index. Qwen3.5 122B-A10B costs 9.1× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.6 or Qwen3.5 122B-A10B?

Qwen3.5 122B-A10B is cheaper. It lists at $0.40 per million input tokens and $3.20 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

Is Claude Opus 4.6 or Qwen3.5 122B-A10B better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 39.1 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 262K.

How many benchmarks do Claude Opus 4.6 and Qwen3.5 122B-A10B share?

25 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Qwen3.5 122B-A10B has 27.

Related comparisons

Go deeper