Noometry

Model comparison

Claude 3 Sonnet vs QwQ-32B

QwQ-32B is the stronger model overall, scoring 39.8 to 29.0 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

QwQ-32B Alibaba (Qwen)

39.8

Rank #159 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where QwQ-32B leads 38.0 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 59.2% for QwQ-32B.
  • QwQ-32B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetQwQ-32B
ProviderAnthropicAlibaba (Qwen)
Noometry Index29.039.8
Released2024-02-292024-11-28
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3036

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

Category by category

Coding QwQ-32B leads

Claude 3 Sonnet: 29.6 (#302), QwQ-32B: 35.4 (#226)

BenchmarkClaude 3 SonnetQwQ-32B
BigCodeBench Instruct42.7%44.6%
LMArena Coding12231333
BigCodeBench Complete53.8%54.4%
Aider Polyglot—20.9%
WeirdML10.2%—
LiveBench Coding—72.2%
HumanEval+64%—
MBPP+69.3%—

Reasoning QwQ-32B leads

Claude 3 Sonnet: 20.5 (#237), QwQ-32B: 23.7 (#174)

BenchmarkClaude 3 SonnetQwQ-32B
LMArena Hard Prompts11971325
Epoch Capabilities Index120.7137.6
Chess Puzzles—5%
LiveBench Reasoning—83.5%
DTBench53.6%—
LiveBench Data Analysis—65%
ForecastBench—58.3
LiveBench—72%
WinoGrande75.1%—

Math QwQ-32B leads

Claude 3 Sonnet: 10.7 (#310), QwQ-32B: 38.0 (#143)

BenchmarkClaude 3 SonnetQwQ-32B
OTIS Mock AIME 2024-20252.5%59.2%
LMArena Math12131359
LiveBench Math—77.8%
MATH Level 518.2%—

Knowledge QwQ-32B leads

Claude 3 Sonnet: 21.1 (#276), QwQ-32B: 37.2 (#158)

BenchmarkClaude 3 SonnetQwQ-32B
GPQA Diamond40.6%65.3%
LMArena Expert11731324
Confabulations—15.6%
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), QwQ-32B: —

BenchmarkClaude 3 SonnetQwQ-32B
LMArena Vision984—

Multilingual QwQ-32B leads

Claude 3 Sonnet: 37.8 (#234), QwQ-32B: 44.8 (#176)

BenchmarkClaude 3 SonnetQwQ-32B
LMArena Non-English12051305
LMArena Chinese11891378
LMArena French12291336
LMArena German12041313
LMArena Japanese11311262
LMArena Korean11281279
LMArena Russian12271297
LMArena Spanish12041354

Instruction Following QwQ-32B leads

Claude 3 Sonnet: 62.8 (#235), QwQ-32B: 72.6 (#137)

BenchmarkClaude 3 SonnetQwQ-32B
LMArena Instruction Following11991297
LiveBench Instruction Following—81.8%

Long Context QwQ-32B leads

Claude 3 Sonnet: 36.7 (#228), QwQ-32B: 49.0 (#11)

BenchmarkClaude 3 SonnetQwQ-32B
LMArena Longer Query12111308
Fiction.LiveBench—83.3%

Writing & Preference QwQ-32B leads

Claude 3 Sonnet: 42.1 (#238), QwQ-32B: 50.6 (#180)

BenchmarkClaude 3 SonnetQwQ-32B
LMArena Text12181329
LMArena Creative Writing11861288
LMArena Multi-Turn12271314
Short-Story Creative Writing—80.2%
EQ-Bench Creative Writing—1257
LiveBench Language—51.4%

Frequently asked questions

Is Claude 3 Sonnet better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.8 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or QwQ-32B better for coding?

QwQ-32B scores higher on coding benchmarks: 35.4 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and QwQ-32B share?

22 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper