Noometry

Model comparison

GPT-4.5 vs Qwen3 32B

Qwen3 32B is the stronger model overall, scoring 38.8 to 36.9 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-4.5 OpenAI

36.9

Rank #200 Confirmed

Qwen3 32B Alibaba (Qwen)

38.8

Rank #166 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-4.5 scores higher in 4 categories and Qwen3 32B in 5 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3 32B leads 40.0 to 32.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 66.9% for Qwen3 32B.
  • Qwen3 32B has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Qwen3 32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index36.938.8
Released2025-02-272025-04
WeightsProprietaryOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.70
Output $ / M tokens—$2.80
Results tracked4226

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

Category by category

Coding GPT-4.5 leads

GPT-4.5: 41.8 (#102), Qwen3 32B: 37.3 (#184)

BenchmarkGPT-4.5Qwen3 32B
Aider Polyglot44.9%40%
LMArena Coding13971358
SciCode—35.4%
WeirdML39.4%—
LiveBench Coding75.2%—

Agentic & Tool Use Qwen3 32B leads

GPT-4.5: 27.6 (#92), Qwen3 32B: 32.3 (#58)

BenchmarkGPT-4.5Qwen3 32B
Berkeley Function Calling Leaderboard—48.7%
Cybench17.5%—

Reasoning Qwen3 32B leads

GPT-4.5: 14.1 (#320), Qwen3 32B: 19.6 (#233)

BenchmarkGPT-4.5Qwen3 32B
LMArena Hard Prompts14041335
Epoch Capabilities Index136.74138.51
ARC-AGI-20.8%—
SimpleBench34.5%—
Kagi LLM Benchmark—54.9%
ARC-AGI-110.3%—
CritPt—0.3%
Chess Puzzles—5%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
DTBench—67.5%
LiveBench Data Analysis64.3%—
LMCA—17.3%
ForecastBench61.7—
LiveBench69%—

Math Qwen3 32B leads

GPT-4.5: 31.0 (#200), Qwen3 32B: 37.9 (#89)

BenchmarkGPT-4.5Qwen3 32B
OTIS Mock AIME 2024-202537.8%66.9%
LMArena Math14121399
LiveBench Math69.3%—
MATH Level 578.6%—

Knowledge Qwen3 32B leads

GPT-4.5: 32.4 (#205), Qwen3 32B: 40.0 (#112)

BenchmarkGPT-4.5Qwen3 32B
GPQA Diamond68.7%65.7%
LMArena Expert13941362
Humanity's Last Exam5.4%—
Confabulations13.6%—
Vectara Hallucination Rate—5.9%

Multimodal Not comparable

GPT-4.5: 37.0 (#68), Qwen3 32B: —

BenchmarkGPT-4.5Qwen3 32B
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.7 (#78), Qwen3 32B: 45.8 (#162)

BenchmarkGPT-4.5Qwen3 32B
LMArena Non-English14131317
LMArena Chinese14211357
LMArena German14571341
LMArena Russian14191311
LMArena French1417—
LMArena Japanese1416—
LMArena Korean1392—

Instruction Following GPT-4.5 leads

GPT-4.5: 72.8 (#129), Qwen3 32B: 69.1 (#174)

BenchmarkGPT-4.5Qwen3 32B
LMArena Instruction Following14041305
LiveBench Instruction Following72.3%—

Long Context Qwen3 32B leads

GPT-4.5: 40.4 (#150), Qwen3 32B: 43.7 (#83)

BenchmarkGPT-4.5Qwen3 32B
Fiction.LiveBench63.9%74.2%
LMArena Longer Query14061327

Writing & Preference GPT-4.5 leads

GPT-4.5: 57.1 (#129), Qwen3 32B: 53.1 (#158)

BenchmarkGPT-4.5Qwen3 32B
LMArena Text14171340
LMArena Creative Writing13941297
LMArena Multi-Turn14441331
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Qwen3 32B?

Qwen3 32B is the stronger model overall, scoring 38.8 to 36.9 on the Noometry Index.

Is GPT-4.5 or Qwen3 32B better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 37.3 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Qwen3 32B share?

18 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen3 32B has 26.

Related comparisons

Go deeper