Noometry

Model comparison

GPT-4.5 vs Qwen3.8 27B

Qwen3.8 27B is the stronger model overall, scoring 45.3 to 36.9 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-4.5 OpenAI

36.9

Rank #200 Confirmed

Qwen3.8 27B Alibaba (Qwen)

45.3

Rank #64 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4.5 scores higher in 0 categories and Qwen3.8 27B in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.8 27B leads 31.5 to 14.1.
  • Qwen3.8 27B has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Qwen3.8 27B
ProviderOpenAIAlibaba (Qwen)
Noometry Index36.945.3
Released2025-02-272026-08-14
WeightsProprietaryOpen
Context window—262K
Max output—33K
Input $ / M tokens—$0.99
Output $ / M tokens—$1.49
Results tracked4228

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

Category by category

Coding Qwen3.8 27B leads

GPT-4.5: 41.8 (#102), Qwen3.8 27B: 50.3 (#42)

BenchmarkGPT-4.5Qwen3.8 27B
LMArena Coding13971487
Aider Polyglot44.9%—
LMArena WebDev—1592
SciCode—46.6%
WeirdML39.4%—
LiveBench Coding75.2%—

Agentic & Tool Use Not comparable

GPT-4.5: 27.6 (#92), Qwen3.8 27B: —

BenchmarkGPT-4.5Qwen3.8 27B
Cybench17.5%—

Reasoning Qwen3.8 27B leads

GPT-4.5: 14.1 (#320), Qwen3.8 27B: 31.5 (#71)

BenchmarkGPT-4.5Qwen3.8 27B
LMArena Hard Prompts14041459
Epoch Capabilities Index136.74149.38
ARC-AGI-20.8%—
SimpleBench34.5%—
NYT Connections (extended)—54.5%
ARC-AGI-110.3%—
CritPt—5.4%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
DTBench—88%
LiveBench Data Analysis64.3%—
LMCA—41.4%
Surface Evolver Bench—45%
ForecastBench61.7—
LiveBench69%—

Math Qwen3.8 27B leads

GPT-4.5: 31.0 (#200), Qwen3.8 27B: 35.7 (#139)

BenchmarkGPT-4.5Qwen3.8 27B
LMArena Math14121453
OTIS Mock AIME 2024-202537.8%—
ProofBench—16%
LiveBench Math69.3%—
MATH Level 578.6%—

Knowledge Qwen3.8 27B leads

GPT-4.5: 32.4 (#205), Qwen3.8 27B: 40.9 (#105)

BenchmarkGPT-4.5Qwen3.8 27B
LMArena Expert13941482
GPQA Diamond68.7%—
Humanity's Last Exam5.4%—
Confabulations13.6%—

Multimodal Qwen3.8 27B leads

GPT-4.5: 37.0 (#68), Qwen3.8 27B: 40.5 (#36)

BenchmarkGPT-4.5Qwen3.8 27B
LMArena Vision11951270
VPCT45%—

Multilingual Qwen3.8 27B leads

GPT-4.5: 52.7 (#78), Qwen3.8 27B: 54.0 (#54)

BenchmarkGPT-4.5Qwen3.8 27B
LMArena Non-English14131431
LMArena Chinese14211504
LMArena French14171468
LMArena German14571435
LMArena Japanese14161392
LMArena Korean13921389
LMArena Russian14191421
LMArena Spanish—1444

Instruction Following Qwen3.8 27B leads

GPT-4.5: 72.8 (#129), Qwen3.8 27B: 75.8 (#54)

BenchmarkGPT-4.5Qwen3.8 27B
LMArena Instruction Following14041436
LiveBench Instruction Following72.3%—

Long Context Qwen3.8 27B leads

GPT-4.5: 40.4 (#150), Qwen3.8 27B: 44.3 (#66)

BenchmarkGPT-4.5Qwen3.8 27B
LMArena Longer Query14061448
Fiction.LiveBench63.9%—

Writing & Preference Qwen3.8 27B leads

GPT-4.5: 57.1 (#129), Qwen3.8 27B: 65.9 (#41)

BenchmarkGPT-4.5Qwen3.8 27B
LMArena Text14171441
LMArena Creative Writing13941382
EQ-Bench Creative Writing12581671
LMArena Multi-Turn14441443
Short-Story Creative Writing75.6%—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Qwen3.8 27B?

Qwen3.8 27B is the stronger model overall, scoring 45.3 to 36.9 on the Noometry Index.

Is GPT-4.5 or Qwen3.8 27B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.3 versus 41.8 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Qwen3.8 27B share?

19 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen3.8 27B has 28.

Related comparisons

Go deeper