Noometry

Model comparison

Claude Sonnet 4.5 vs Qwen3 Coder Next

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 34.3 on the Noometry Index. Qwen3 Coder Next costs 21× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 3 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

Qwen3 Coder Next Alibaba (Qwen)

34.3

Rank #232 Reported

Summary

  • They share 3 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 2 categories and Qwen3 Coder Next in 0 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Claude Sonnet 4.5 leads 47.3 to 36.3.
  • The biggest single-benchmark swing is WeirdML: 47.7% for Claude Sonnet 4.5 and 34.4% for Qwen3 Coder Next.
  • Qwen3 Coder Next is cheaper at $0.12 / $0.80 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Qwen3 Coder Next accepts more context: 262K tokens versus 200K.
  • Qwen3 Coder Next has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5Qwen3 Coder Next
ProviderAnthropicAlibaba (Qwen)
Noometry Index44.134.3
Released2025-09-292026-02-02
WeightsProprietaryOpen
Context window200K262K
Max output64K66K
Input $ / M tokens$3$0.12
Output $ / M tokens$15$0.80
Results tracked733

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

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.3 (#61), Qwen3 Coder Next: 36.3 (#210)

BenchmarkClaude Sonnet 4.5Qwen3 Coder Next
SciCode44.7%32.3%
WeirdML47.7%34.4%
SWE-bench Verified71.3%—
SWE-bench Verified (bash only)71.4%—
LMArena WebDev1393—
SWE-bench Multilingual67%—
GSO14.7%—
LMArena Coding1489—
ALE-Bench796.15—
AlgoTune1.52—

Agentic & Tool Use Not comparable

Claude Sonnet 4.5: 38.3 (#32), Qwen3 Coder Next: —

BenchmarkClaude Sonnet 4.5Qwen3 Coder Next
Terminal-Bench46.5%—
Berkeley Function Calling Leaderboard73.2%—
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
LMArena Search1159—
METR Time Horizons67.4%—
Vending-Bench 23,839—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#125), Qwen3 Coder Next: 22.4 (#196)

BenchmarkClaude Sonnet 4.5Qwen3 Coder Next
CritPt1.1%0%
ARC-AGI-213.6%—
SimpleBench54.3%—
Kagi LLM Benchmark57.9%—
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
Chess Puzzles12%—
EnigmaEval6%—
EBR-Bench2.4%—
LMArena Hard Prompts1462—
Mystery Game Puzzles17%—
DTBench83.2%—
LMCA38.8%—
Epoch Capabilities Index146.84—
ForecastBench61.9—

Math Not comparable

Claude Sonnet 4.5: 32.3 (#216), Qwen3 Coder Next: —

BenchmarkClaude Sonnet 4.5Qwen3 Coder Next
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
OTIS Mock AIME 2024-202577.8%—
ProofBench19%—
Omni-MATH55.3%—
LMArena Math1449—
MATH Level 597.7%—
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Not comparable

Claude Sonnet 4.5: 48.4 (#76), Qwen3 Coder Next: —

BenchmarkClaude Sonnet 4.5Qwen3 Coder Next
GPQA Diamond82.3%—
Humanity's Last Exam13.7%—
SimpleQA Verified30.7%—
MMLU-Pro86.9%—
Vectara Hallucination Rate12%—
GPQA (HELM)68.6%—
LMArena Expert1482—

Multimodal Not comparable

Claude Sonnet 4.5: 34.8 (#89), Qwen3 Coder Next: —

BenchmarkClaude Sonnet 4.5Qwen3 Coder Next
VPCT39.8%—
LMArena Document1450—

Multilingual Not comparable

Claude Sonnet 4.5: 53.4 (#69), Qwen3 Coder Next: —

BenchmarkClaude Sonnet 4.5Qwen3 Coder Next
LMArena Non-English1425—
LMArena Chinese1459—
LMArena French1458—
LMArena German1427—
LMArena Japanese1390—
LMArena Korean1403—
LMArena Russian1437—
LMArena Spanish1457—

Instruction Following Not comparable

Claude Sonnet 4.5: 75.0 (#78), Qwen3 Coder Next: —

BenchmarkClaude Sonnet 4.5Qwen3 Coder Next
IFEval85%—
LMArena Instruction Following1459—

Long Context Not comparable

Claude Sonnet 4.5: 45.2 (#46), Qwen3 Coder Next: —

BenchmarkClaude Sonnet 4.5Qwen3 Coder Next
LMArena Longer Query1476—

Writing & Preference Not comparable

Claude Sonnet 4.5: 66.5 (#34), Qwen3 Coder Next: —

BenchmarkClaude Sonnet 4.5Qwen3 Coder Next
LMArena Text1439—
LMArena Creative Writing1442—
EQ-Bench Creative Writing1678—
WildBench85.4%—
LMArena Multi-Turn1465—

Frequently asked questions

Is Claude Sonnet 4.5 better than Qwen3 Coder Next?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 34.3 on the Noometry Index. Qwen3 Coder Next costs 21× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 or Qwen3 Coder Next?

Qwen3 Coder Next is cheaper. It lists at $0.12 per million input tokens and $0.80 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Qwen3 Coder Next better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 36.3 in the Noometry coding category.

Which has the bigger context window?

Qwen3 Coder Next does, with 262K tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and Qwen3 Coder Next share?

3 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Qwen3 Coder Next has 3.

Related comparisons

Go deeper