Noometry

Model comparison

GPT-4.5 vs Qwen Max

GPT-4.5 is the stronger model overall, scoring 37.2 to 34.7 on the Noometry Index.

Last verified . 21 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Qwen Max Alibaba (Qwen)

34.7

Rank #230 Confirmed

Summary

  • They share 21 benchmarks with published results for both. GPT-4.5 scores higher in 7 categories and Qwen Max in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where GPT-4.5 leads 42.2 to 30.7.
  • The biggest single-benchmark swing is Aider Polyglot: 44.9% for GPT-4.5 and 21.8% for Qwen Max.

Side by side

GPT-4.5Qwen Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index37.234.7
Released2025-02-272024-04-03
WeightsProprietaryProprietary
Context window—33K
Max output—8K
Input $ / M tokens—$1.60
Output $ / M tokens—$6.40
Results tracked4223

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), Qwen Max: 30.7 (#292)

BenchmarkGPT-4.5Qwen Max
Aider Polyglot44.9%21.8%
LMArena Coding13961288
WeirdML39.4%—
LiveBench Coding75.2%—

Agentic & Tool Use Not comparable

GPT-4.5: 27.9 (#97), Qwen Max: —

BenchmarkGPT-4.5Qwen Max
Cybench17.5%—

Reasoning Qwen Max leads

GPT-4.5: 13.9 (#330), Qwen Max: 25.1 (#151)

BenchmarkGPT-4.5Qwen Max
LMArena Hard Prompts14031269
ARC-AGI-20.8%—
SimpleBench34.5%—
ARC-AGI-110.3%—
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
LiveBench Data Analysis64.3%—
Epoch Capabilities Index136.74—
ForecastBench61.7—
LiveBench69%—

Math GPT-4.5 leads

GPT-4.5: 32.6 (#211), Qwen Max: 22.3 (#276)

BenchmarkGPT-4.5Qwen Max
OTIS Mock AIME 2024-202537.8%16.1%
LMArena Math14121275
MATH Level 578.6%67.2%
LiveBench Math69.3%—
FrontierMath (Feb 2025 set)—1%

Knowledge GPT-4.5 leads

GPT-4.5: 32.5 (#211), Qwen Max: 30.3 (#228)

BenchmarkGPT-4.5Qwen Max
GPQA Diamond68.7%56.1%
LMArena Expert13941248
Humanity's Last Exam5.4%—
Confabulations13.6%—

Multimodal Not comparable

GPT-4.5: 37.6 (#71), Qwen Max: —

BenchmarkGPT-4.5Qwen Max
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), Qwen Max: 41.8 (#202)

BenchmarkGPT-4.5Qwen Max
LMArena Non-English14131263
LMArena Chinese14211254
LMArena French14181330
LMArena German14571254
LMArena Japanese14161205
LMArena Korean13921142
LMArena Russian14191274
LMArena Spanish—1290

Instruction Following GPT-4.5 leads

GPT-4.5: 72.6 (#134), Qwen Max: 66.5 (#208)

BenchmarkGPT-4.5Qwen Max
LMArena Instruction Following14041262
LiveBench Instruction Following72.3%—

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#155), Qwen Max: 39.4 (#180)

BenchmarkGPT-4.5Qwen Max
Fiction.LiveBench63.9%66.7%
LMArena Longer Query14061288

Writing & Preference GPT-4.5 leads

GPT-4.5: 56.9 (#134), Qwen Max: 47.8 (#205)

BenchmarkGPT-4.5Qwen Max
LMArena Text14171282
LMArena Creative Writing13941248
LMArena Multi-Turn14441277
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Qwen Max?

GPT-4.5 is the stronger model overall, scoring 37.2 to 34.7 on the Noometry Index.

Is GPT-4.5 or Qwen Max better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 30.7 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Qwen Max share?

21 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen Max has 23.

Related comparisons

Go deeper