Noometry

Model comparison

GPT-4.1 vs Qwen1.5-32B

GPT-4.1 is the stronger model overall, scoring 35.9 to 30.5 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-4.1 OpenAI

35.9

Rank #219 Confirmed

Qwen1.5-32B Alibaba (Qwen)

30.5

Rank #293 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-4.1 scores higher in 6 categories and Qwen1.5-32B in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4.1 leads 37.1 to 13.5.
  • The biggest single-benchmark swing is GPQA Diamond: 66.9% for GPT-4.1 and 30.7% for Qwen1.5-32B.
  • Qwen1.5-32B has downloadable open weights; the other is API-only.

Side by side

GPT-4.1Qwen1.5-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index35.930.5
Released2025-04-142024-02-04
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$2—
Output $ / M tokens$8—
Results tracked5221

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

Category by category

Coding GPT-4.1 leads

GPT-4.1: 34.4 (#238), Qwen1.5-32B: 31.7 (#282)

BenchmarkGPT-4.1Qwen1.5-32B
LMArena Coding13911155
SWE-bench Verified48.5%—
SWE-bench Verified (bash only)39.6%—
Aider Polyglot52.4%—
WeirdML39%—
BigCodeBench Instruct—32.3%
BigCodeBench Complete—42%
CadEval42%—
ALE-Bench558.1—

Agentic & Tool Use Not comparable

GPT-4.1: 34.7 (#43), Qwen1.5-32B: —

BenchmarkGPT-4.1Qwen1.5-32B
Berkeley Function Calling Leaderboard54%—

Reasoning Qwen1.5-32B leads

GPT-4.1: 11.7 (#339), Qwen1.5-32B: 21.8 (#212)

BenchmarkGPT-4.1Qwen1.5-32B
LMArena Hard Prompts13841130
ARC-AGI-20.4%—
SimpleBench27%—
Kagi LLM Benchmark52.3%—
ARC-AGI-15.5%—
Chess Puzzles6%—
EnigmaEval2.2%—
DTBench68.3%—
LMCA25.6%—
Epoch Capabilities Index136.78—
ForecastBench61.5—

Math Qwen1.5-32B leads

GPT-4.1: 22.3 (#280), Qwen1.5-32B: 33.0 (#207)

BenchmarkGPT-4.1Qwen1.5-32B
LMArena Math13701155
FrontierMath (Tiers 1-3)6%—
OTIS Mock AIME 2024-202538.3%—
Omni-MATH47.1%—
MATH Level 583%—
FrontierMath (Feb 2025 set)5.5%—
FrontierMath Tier 4 (v1)0%—

Knowledge GPT-4.1 leads

GPT-4.1: 37.1 (#160), Qwen1.5-32B: 13.5 (#296)

BenchmarkGPT-4.1Qwen1.5-32B
GPQA Diamond66.9%30.7%
LMArena Expert13641126
Humanity's Last Exam5.4%—
SimpleQA Verified31.1%—
MMLU-Pro81.1%—
Vectara Hallucination Rate5.6%—
GPQA (HELM)65.9%—
MMLU—74.4%

Multimodal Not comparable

GPT-4.1: 38.2 (#67), Qwen1.5-32B: —

BenchmarkGPT-4.1Qwen1.5-32B
LMArena Vision1211—
GeoBench72%—

Multilingual GPT-4.1 leads

GPT-4.1: 49.4 (#133), Qwen1.5-32B: 31.4 (#259)

BenchmarkGPT-4.1Qwen1.5-32B
LMArena Non-English13701106
LMArena Chinese13821177
LMArena French13821101
LMArena German13811058
LMArena Japanese13191027
LMArena Korean13391008
LMArena Russian13771073
LMArena Spanish13761089

Instruction Following GPT-4.1 leads

GPT-4.1: 71.3 (#153), Qwen1.5-32B: 57.7 (#265)

BenchmarkGPT-4.1Qwen1.5-32B
LMArena Instruction Following13671116
IFEval83.8%—

Long Context GPT-4.1 leads

GPT-4.1: 40.0 (#163), Qwen1.5-32B: 34.7 (#246)

BenchmarkGPT-4.1Qwen1.5-32B
LMArena Longer Query13851146
Fiction.LiveBench63.9%—

Writing & Preference GPT-4.1 leads

GPT-4.1: 57.6 (#125), Qwen1.5-32B: 34.2 (#271)

BenchmarkGPT-4.1Qwen1.5-32B
LMArena Text13831137
LMArena Creative Writing13631083
LMArena Multi-Turn13981140
EQ-Bench Creative Writing1420—
WildBench85.4%—

Frequently asked questions

Is GPT-4.1 better than Qwen1.5-32B?

GPT-4.1 is the stronger model overall, scoring 35.9 to 30.5 on the Noometry Index.

Is GPT-4.1 or Qwen1.5-32B better for coding?

GPT-4.1 scores higher on coding benchmarks: 34.4 versus 31.7 in the Noometry coding category.

How many benchmarks do GPT-4.1 and Qwen1.5-32B share?

18 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Qwen1.5-32B has 21.

Related comparisons

Go deeper