Noometry

Model comparison

GPT-4.5 vs Qwen2-72B

GPT-4.5 is the stronger model overall, scoring 37.2 to 30.0 on the Noometry Index.

Last verified . 20 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 20 benchmarks with published results for both. GPT-4.5 scores higher in 8 categories and Qwen2-72B in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where GPT-4.5 leads 52.5 to 35.9.
  • The biggest single-benchmark swing is MATH Level 5: 78.6% for GPT-4.5 and 39.1% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Qwen2-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index37.230.0
Released2025-02-272024-06-07
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
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: 42.2 (#109), Qwen2-72B: 29.1 (#310)

BenchmarkGPT-4.5Qwen2-72B
WeirdML39.4%11.3%
LMArena Coding13961196
Aider Polyglot44.9%—
BigCodeBench Instruct—38.5%
LiveBench Coding75.2%—
BigCodeBench Complete—54%

Agentic & Tool Use GPT-4.5 leads

GPT-4.5: 27.9 (#97), Qwen2-72B: 17.0 (#146)

BenchmarkGPT-4.5Qwen2-72B
TheAgentCompany—1.1%
Cybench17.5%—
METR Time Horizons—29.9%

Reasoning Qwen2-72B leads

GPT-4.5: 13.9 (#330), Qwen2-72B: 23.2 (#181)

BenchmarkGPT-4.5Qwen2-72B
LMArena Hard Prompts14031191
Epoch Capabilities Index136.74125.28
ARC-AGI-20.8%—
SimpleBench34.5%—
ARC-AGI-110.3%—
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
LiveBench Data Analysis64.3%—
ForecastBench61.7—
LiveBench69%—

Math GPT-4.5 leads

GPT-4.5: 32.6 (#211), Qwen2-72B: 30.2 (#236)

BenchmarkGPT-4.5Qwen2-72B
LMArena Math14121235
MATH Level 578.6%39.1%
OTIS Mock AIME 2024-202537.8%—
LiveBench Math69.3%—

Knowledge GPT-4.5 leads

GPT-4.5: 32.5 (#211), Qwen2-72B: 21.2 (#275)

BenchmarkGPT-4.5Qwen2-72B
GPQA Diamond68.7%40.8%
LMArena Expert13941171
Humanity's Last Exam5.4%—
Confabulations13.6%—
MMLU—82.4%

Multimodal Not comparable

GPT-4.5: 37.6 (#71), Qwen2-72B: —

BenchmarkGPT-4.5Qwen2-72B
LMArena Vision1195—
VPCT45%—

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), Qwen2-72B: 35.9 (#244)

BenchmarkGPT-4.5Qwen2-72B
LMArena Non-English14131176
LMArena Chinese14211240
LMArena French14181170
LMArena German14571151
LMArena Japanese14161111
LMArena Korean13921083
LMArena Russian14191169
LMArena Spanish—1169

Instruction Following GPT-4.5 leads

GPT-4.5: 72.6 (#134), Qwen2-72B: 61.7 (#241)

BenchmarkGPT-4.5Qwen2-72B
LMArena Instruction Following14041181
LiveBench Instruction Following72.3%—

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#155), Qwen2-72B: 36.1 (#235)

BenchmarkGPT-4.5Qwen2-72B
LMArena Longer Query14061192
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.5 leads

GPT-4.5: 56.9 (#134), Qwen2-72B: 40.8 (#241)

BenchmarkGPT-4.5Qwen2-72B
LMArena Text14171203
LMArena Creative Writing13941181
LMArena Multi-Turn14441196
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Qwen2-72B?

GPT-4.5 is the stronger model overall, scoring 37.2 to 30.0 on the Noometry Index.

Is GPT-4.5 or Qwen2-72B better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 29.1 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Qwen2-72B share?

20 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper