Noometry

Model comparison

Claude 3 Sonnet vs Qwen3 Max

Qwen3 Max is the stronger model overall, scoring 43.7 to 29.0 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Qwen3 Max Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3 Max leads 38.7 to 10.7.
  • The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 97.1% for Qwen3 Max.

Side by side

Claude 3 SonnetQwen3 Max
ProviderAnthropicAlibaba (Qwen)
Noometry Index29.043.7
Released2024-02-292025-09-23
WeightsProprietaryProprietary
Context window—262K
Max output—66K
Input $ / M tokens—$1.20
Output $ / M tokens—$6
Results tracked3033

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

Category by category

Coding Qwen3 Max leads

Claude 3 Sonnet: 29.6 (#302), Qwen3 Max: 43.0 (#93)

BenchmarkClaude 3 SonnetQwen3 Max
LMArena Coding12231456
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
ALE-Bench—370.45
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, Qwen3 Max: —

BenchmarkClaude 3 SonnetQwen3 Max
Vending-Bench 2—71.56

Reasoning Qwen3 Max leads

Claude 3 Sonnet: 20.5 (#237), Qwen3 Max: 22.6 (#190)

BenchmarkClaude 3 SonnetQwen3 Max
LMArena Hard Prompts11971448
DTBench53.6%82.1%
Epoch Capabilities Index120.7142.38
Kagi LLM Benchmark—72.5%
NYT Connections (extended)—30.1%
Chess Puzzles—4%
Mystery Game Puzzles—5%
LMCA—28.3%
WinoGrande75.1%—

Math Qwen3 Max leads

Claude 3 Sonnet: 10.7 (#310), Qwen3 Max: 38.7 (#131)

BenchmarkClaude 3 SonnetQwen3 Max
OTIS Mock AIME 2024-20252.5%73.3%
LMArena Math12131446
MATH Level 518.2%97.1%
FrontierMath (Tiers 1-3)—18.9%

Knowledge Qwen3 Max leads

Claude 3 Sonnet: 21.1 (#276), Qwen3 Max: 48.1 (#78)

BenchmarkClaude 3 SonnetQwen3 Max
GPQA Diamond40.6%72.6%
LMArena Expert11731455
SimpleQA Verified—48.7%
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Qwen3 Max: —

BenchmarkClaude 3 SonnetQwen3 Max
LMArena Vision984—

Multilingual Qwen3 Max leads

Claude 3 Sonnet: 37.8 (#234), Qwen3 Max: 53.7 (#62)

BenchmarkClaude 3 SonnetQwen3 Max
LMArena Non-English12051429
LMArena Chinese11891478
LMArena French12291449
LMArena German12041463
LMArena Japanese11311397
LMArena Korean11281399
LMArena Russian12271428
LMArena Spanish12041462

Instruction Following Qwen3 Max leads

Claude 3 Sonnet: 62.8 (#235), Qwen3 Max: 74.8 (#87)

BenchmarkClaude 3 SonnetQwen3 Max
LMArena Instruction Following11991419

Long Context Qwen3 Max leads

Claude 3 Sonnet: 36.7 (#228), Qwen3 Max: 41.6 (#134)

BenchmarkClaude 3 SonnetQwen3 Max
LMArena Longer Query12111438
Fiction.LiveBench—66.7%
CL-bench—14.5%

Writing & Preference Qwen3 Max leads

Claude 3 Sonnet: 42.1 (#238), Qwen3 Max: 62.4 (#76)

BenchmarkClaude 3 SonnetQwen3 Max
LMArena Text12181439
LMArena Creative Writing11861402
LMArena Multi-Turn12271446

Frequently asked questions

Is Claude 3 Sonnet better than Qwen3 Max?

Qwen3 Max is the stronger model overall, scoring 43.7 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Qwen3 Max better for coding?

Qwen3 Max scores higher on coding benchmarks: 43.0 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Qwen3 Max share?

22 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper