Noometry

Model comparison

GPT-4.5 vs Qwen3.6 Plus

Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 36.9 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-4.5 OpenAI

36.9

Rank #200 Confirmed

Qwen3.6 Plus Alibaba (Qwen)

47.3

Rank #54 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4.5 scores higher in 1 category and Qwen3.6 Plus in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 32.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 93.3% for Qwen3.6 Plus.

Side by side

GPT-4.5Qwen3.6 Plus
ProviderOpenAIAlibaba (Qwen)
Noometry Index36.947.3
Released2025-02-272026-03-31
WeightsProprietaryProprietary
Context window—1M
Max output—66K
Input $ / M tokens—$0.50
Output $ / M tokens—$3
Results tracked4237

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), Qwen3.6 Plus: 40.6 (#125)

BenchmarkGPT-4.5Qwen3.6 Plus
LMArena Coding13971467
SWE-bench Verified—57.9%
Aider Polyglot44.9%—
LMArena WebDev—1461
SciCode—40.7%
WeirdML39.4%—
LiveBench Coding75.2%—
ALE-Bench—670.15

Agentic & Tool Use Not comparable

GPT-4.5: 27.6 (#92), Qwen3.6 Plus: —

BenchmarkGPT-4.5Qwen3.6 Plus
Cybench17.5%—
Vending-Bench 2—5,115

Reasoning Qwen3.6 Plus leads

GPT-4.5: 14.1 (#320), Qwen3.6 Plus: 28.5 (#89)

BenchmarkGPT-4.5Qwen3.6 Plus
LMArena Hard Prompts14041449
Epoch Capabilities Index136.74147.67
ARC-AGI-20.8%—
SimpleBench34.5%—
NYT Connections (extended)—60.3%
ARC-AGI-110.3%—
CritPt—2.9%
Chess Puzzles—17%
EnigmaEval3.2%—
Thematic Generalization—59.5%
LiveBench Reasoning71.1%—
Mystery Game Puzzles—12%
DTBench—81.9%
LiveBench Data Analysis64.3%—
LMCA—33.1%
ForecastBench61.7—
LiveBench69%—

Math Qwen3.6 Plus leads

GPT-4.5: 31.0 (#200), Qwen3.6 Plus: 50.6 (#44)

BenchmarkGPT-4.5Qwen3.6 Plus
OTIS Mock AIME 2024-202537.8%93.3%
LMArena Math14121450
FrontierMath (Tiers 1-3)—38.2%
LiveBench Math69.3%—
MATH Level 578.6%—
FrontierMath (Feb 2025 set)—26.2%
FrontierMath Tier 4 (v1)—8.3%

Knowledge Qwen3.6 Plus leads

GPT-4.5: 32.4 (#205), Qwen3.6 Plus: 56.1 (#40)

BenchmarkGPT-4.5Qwen3.6 Plus
GPQA Diamond68.7%88.4%
LMArena Expert13941456
Humanity's Last Exam5.4%—
SimpleQA Verified—44.1%
Confabulations13.6%—

Multimodal Not comparable

GPT-4.5: 37.0 (#68), Qwen3.6 Plus: —

BenchmarkGPT-4.5Qwen3.6 Plus
LMArena Vision1195—
VPCT45%—

Multilingual Too close to call

GPT-4.5: 52.7 (#78), Qwen3.6 Plus: 53.5 (#66)

BenchmarkGPT-4.5Qwen3.6 Plus
LMArena Non-English14131424
LMArena Chinese14211478
LMArena French14171454
LMArena German14571451
LMArena Japanese14161389
LMArena Korean13921381
LMArena Russian14191434
LMArena Spanish—1432

Instruction Following Qwen3.6 Plus leads

GPT-4.5: 72.8 (#129), Qwen3.6 Plus: 75.2 (#70)

BenchmarkGPT-4.5Qwen3.6 Plus
LMArena Instruction Following14041425
LiveBench Instruction Following72.3%—

Long Context Qwen3.6 Plus leads

GPT-4.5: 40.4 (#150), Qwen3.6 Plus: 45.1 (#48)

BenchmarkGPT-4.5Qwen3.6 Plus
LMArena Longer Query14061440
Fiction.LiveBench63.9%—
CL-bench—20.3%

Writing & Preference Qwen3.6 Plus leads

GPT-4.5: 57.1 (#129), Qwen3.6 Plus: 62.4 (#78)

BenchmarkGPT-4.5Qwen3.6 Plus
LMArena Text14171437
LMArena Creative Writing13941405
LMArena Multi-Turn14441438
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Qwen3.6 Plus?

Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 36.9 on the Noometry Index.

Is GPT-4.5 or Qwen3.6 Plus better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 40.6 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Qwen3.6 Plus share?

19 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen3.6 Plus has 37.

Related comparisons

Go deeper