Noometry

Model comparison

GPT-4.5 vs Qwen2.5-Coder-32B

GPT-4.5 is the stronger model overall, scoring 37.2 to 33.4 on the Noometry Index.

Last verified . 21 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Qwen2.5-Coder-32B Alibaba (Qwen)

33.4

Rank #245 Confirmed

Summary

  • They share 21 benchmarks with published results for both. GPT-4.5 scores higher in 5 categories and Qwen2.5-Coder-32B in 3 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in coding, where GPT-4.5 leads 42.2 to 22.6.
  • The biggest single-benchmark swing is LiveBench Language: 61.5% for GPT-4.5 and 23.3% for Qwen2.5-Coder-32B.
  • Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Qwen2.5-Coder-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index37.233.4
Released2025-02-272024-09-18
WeightsProprietaryOpen
Context window—33K
Max output—29K
Input $ / M tokens—$0.66
Output $ / M tokens—$1
Results tracked4231

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), Qwen2.5-Coder-32B: 22.6 (#333)

BenchmarkGPT-4.5Qwen2.5-Coder-32B
Aider Polyglot44.9%16.4%
LiveBench Coding75.2%56.9%
LMArena Coding13961276
SWE-bench Verified (bash only)—9%
WeirdML39.4%—
BigCodeBench Instruct—49%
BigCodeBench Complete—58%
HumanEval+—87.2%
MBPP+—77%

Agentic & Tool Use Not comparable

GPT-4.5: 27.9 (#97), Qwen2.5-Coder-32B: —

BenchmarkGPT-4.5Qwen2.5-Coder-32B
Cybench17.5%—

Reasoning Qwen2.5-Coder-32B leads

GPT-4.5: 13.9 (#330), Qwen2.5-Coder-32B: 21.2 (#225)

BenchmarkGPT-4.5Qwen2.5-Coder-32B
LiveBench Reasoning71.1%42.1%
LMArena Hard Prompts14031251
LiveBench Data Analysis64.3%49.9%
Epoch Capabilities Index136.74119.49
LiveBench69%46.2%
ARC-AGI-20.8%—
SimpleBench34.5%—
ARC-AGI-110.3%—
EnigmaEval3.2%—
ForecastBench61.7—
HellaSwag—83%
WinoGrande—80.8%

Math Too close to call

GPT-4.5: 32.6 (#211), Qwen2.5-Coder-32B: 33.3 (#204)

BenchmarkGPT-4.5Qwen2.5-Coder-32B
LiveBench Math69.3%46.6%
LMArena Math14121251
OTIS Mock AIME 2024-202537.8%—
MATH Level 578.6%—
GSM8K—93%

Knowledge Too close to call

GPT-4.5: 32.5 (#211), Qwen2.5-Coder-32B: 33.4 (#203)

BenchmarkGPT-4.5Qwen2.5-Coder-32B
LMArena Expert13941221
GPQA Diamond68.7%—
Humanity's Last Exam5.4%—
Confabulations13.6%—
ARC (AI2) Challenge—70.5%
MMLU—79.1%

Multimodal Not comparable

GPT-4.5: 37.6 (#71), Qwen2.5-Coder-32B: —

BenchmarkGPT-4.5Qwen2.5-Coder-32B
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), Qwen2.5-Coder-32B: 37.8 (#235)

BenchmarkGPT-4.5Qwen2.5-Coder-32B
LMArena Non-English14131205
LMArena Chinese14211222
LMArena Russian14191228
LMArena French1418—
LMArena German1457—
LMArena Japanese1416—
LMArena Korean1392—

Instruction Following GPT-4.5 leads

GPT-4.5: 72.6 (#134), Qwen2.5-Coder-32B: 61.4 (#245)

BenchmarkGPT-4.5Qwen2.5-Coder-32B
LiveBench Instruction Following72.3%58.7%
LMArena Instruction Following14041223

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#155), Qwen2.5-Coder-32B: 38.0 (#208)

BenchmarkGPT-4.5Qwen2.5-Coder-32B
LMArena Longer Query14061251
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.5 leads

GPT-4.5: 56.9 (#134), Qwen2.5-Coder-32B: 41.6 (#240)

BenchmarkGPT-4.5Qwen2.5-Coder-32B
LMArena Text14171230
LMArena Creative Writing13941174
LMArena Multi-Turn14441222
LiveBench Language61.5%23.3%
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—

Frequently asked questions

Is GPT-4.5 better than Qwen2.5-Coder-32B?

GPT-4.5 is the stronger model overall, scoring 37.2 to 33.4 on the Noometry Index.

Is GPT-4.5 or Qwen2.5-Coder-32B better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 22.6 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Qwen2.5-Coder-32B share?

21 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen2.5-Coder-32B has 31.

Related comparisons

Go deeper