Noometry

Model comparison

GPT-4.5 vs QwQ-32B

QwQ-32B is the stronger model overall, scoring 39.8 to 37.2 on the Noometry Index.

Last verified . 32 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

QwQ-32B Alibaba (Qwen)

39.8

Rank #159 Confirmed

Summary

  • They share 32 benchmarks with published results for both. GPT-4.5 scores higher in 4 categories and QwQ-32B in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where QwQ-32B leads 23.7 to 13.9.
  • The biggest single-benchmark swing is Aider Polyglot: 44.9% for GPT-4.5 and 20.9% for QwQ-32B.
  • QwQ-32B has downloadable open weights; the other is API-only.

Side by side

GPT-4.5QwQ-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index37.239.8
Released2025-02-272024-11-28
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4236

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

Category by category

Coding GPT-4.5 leads

GPT-4.5: 42.2 (#109), QwQ-32B: 35.4 (#226)

BenchmarkGPT-4.5QwQ-32B
Aider Polyglot44.9%20.9%
LiveBench Coding75.2%72.2%
LMArena Coding13961333
WeirdML39.4%—
BigCodeBench Instruct—44.6%
BigCodeBench Complete—54.4%

Agentic & Tool Use Not comparable

GPT-4.5: 27.9 (#97), QwQ-32B: —

BenchmarkGPT-4.5QwQ-32B
Cybench17.5%—

Reasoning QwQ-32B leads

GPT-4.5: 13.9 (#330), QwQ-32B: 23.7 (#174)

BenchmarkGPT-4.5QwQ-32B
LiveBench Reasoning71.1%83.5%
LMArena Hard Prompts14031325
LiveBench Data Analysis64.3%65%
Epoch Capabilities Index136.74137.6
ForecastBench61.758.3
LiveBench69%72%
ARC-AGI-20.8%—
SimpleBench34.5%—
ARC-AGI-110.3%—
Chess Puzzles—5%
EnigmaEval3.2%—

Math QwQ-32B leads

GPT-4.5: 32.6 (#211), QwQ-32B: 38.0 (#143)

BenchmarkGPT-4.5QwQ-32B
OTIS Mock AIME 2024-202537.8%59.2%
LiveBench Math69.3%77.8%
LMArena Math14121359
MATH Level 578.6%—

Knowledge QwQ-32B leads

GPT-4.5: 32.5 (#211), QwQ-32B: 37.2 (#158)

BenchmarkGPT-4.5QwQ-32B
GPQA Diamond68.7%65.3%
Confabulations13.6%15.6%
LMArena Expert13941324
Humanity's Last Exam5.4%—

Multimodal Not comparable

GPT-4.5: 37.6 (#71), QwQ-32B: —

BenchmarkGPT-4.5QwQ-32B
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), QwQ-32B: 44.8 (#176)

BenchmarkGPT-4.5QwQ-32B
LMArena Non-English14131305
LMArena Chinese14211378
LMArena French14181336
LMArena German14571313
LMArena Japanese14161262
LMArena Korean13921279
LMArena Russian14191297
LMArena Spanish—1354

Instruction Following Too close to call

GPT-4.5: 72.6 (#134), QwQ-32B: 72.6 (#137)

BenchmarkGPT-4.5QwQ-32B
LiveBench Instruction Following72.3%81.8%
LMArena Instruction Following14041297

Long Context QwQ-32B leads

GPT-4.5: 40.4 (#155), QwQ-32B: 49.0 (#11)

BenchmarkGPT-4.5QwQ-32B
Fiction.LiveBench63.9%83.3%
LMArena Longer Query14061308

Writing & Preference GPT-4.5 leads

GPT-4.5: 56.9 (#134), QwQ-32B: 50.6 (#180)

BenchmarkGPT-4.5QwQ-32B
LMArena Text14171329
LMArena Creative Writing13941288
Short-Story Creative Writing75.6%80.2%
EQ-Bench Creative Writing12581257
LMArena Multi-Turn14441314
LiveBench Language61.5%51.4%

Frequently asked questions

Is GPT-4.5 better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.8 to 37.2 on the Noometry Index.

Is GPT-4.5 or QwQ-32B better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 35.4 in the Noometry coding category.

How many benchmarks do GPT-4.5 and QwQ-32B share?

32 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper