Noometry

Model comparison

GPT-5 Mini vs Qwen3 32B

GPT-5 Mini is the stronger model overall, scoring 41.7 to 38.8 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-5 Mini OpenAI

41.7

Rank #115 Confirmed

Qwen3 32B Alibaba (Qwen)

38.8

Rank #166 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-5 Mini scores higher in 7 categories and Qwen3 32B in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5 Mini leads 46.3 to 37.9.
  • The biggest single-benchmark swing is Chess Puzzles: 30% for GPT-5 Mini and 5% for Qwen3 32B.
  • GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
  • GPT-5 Mini accepts more context: 400K tokens versus 131K.
  • Qwen3 32B has downloadable open weights; the other is API-only.

Side by side

GPT-5 MiniQwen3 32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index41.738.8
Released2025-08-072025-04
WeightsProprietaryOpen
Context window400K131K
Max output128K16K
Input $ / M tokens$0.25$0.70
Output $ / M tokens$2$2.80
Results tracked6026

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

Category by category

Coding GPT-5 Mini leads

GPT-5 Mini: 40.0 (#134), Qwen3 32B: 37.3 (#184)

BenchmarkGPT-5 MiniQwen3 32B
SciCode39.2%35.4%
LMArena Coding14061358
SWE-bench Verified64.7%—
SWE-bench Verified (bash only)59.8%—
Aider Polyglot—40%
SWE-bench Multilingual39.7%—
WeirdML52.7%—
ALE-Bench799.77—
AlgoTune1.38—

Agentic & Tool Use Qwen3 32B leads

GPT-5 Mini: 31.0 (#64), Qwen3 32B: 32.3 (#58)

BenchmarkGPT-5 MiniQwen3 32B
Berkeley Function Calling Leaderboard55.5%48.7%
Terminal-Bench34.8%—
Vending-Bench 2-31.18—

Reasoning GPT-5 Mini leads

GPT-5 Mini: 24.1 (#153), Qwen3 32B: 19.6 (#233)

BenchmarkGPT-5 MiniQwen3 32B
Kagi LLM Benchmark70.3%54.9%
CritPt0%0.3%
Chess Puzzles30%5%
LMArena Hard Prompts13801335
DTBench80.5%67.5%
LMCA34.2%17.3%
Epoch Capabilities Index145.51138.51
ARC-AGI-24.4%—
ARC-AGI-154.3%—
EnigmaEval8.2%—
Mystery Game Puzzles10%—
ForecastBench61—

Math GPT-5 Mini leads

GPT-5 Mini: 46.3 (#59), Qwen3 32B: 37.9 (#89)

BenchmarkGPT-5 MiniQwen3 32B
OTIS Mock AIME 2024-202586.7%66.9%
LMArena Math13771399
FrontierMath (Tiers 1-3)46.7%—
FrontierMath Tier 412.2%—
ProofBench9%—
Omni-MATH72.2%—
MATH Level 597.8%—
FrontierMath (Feb 2025 set)27.2%—
FrontierMath Tier 4 (v1)6.3%—

Knowledge GPT-5 Mini leads

GPT-5 Mini: 45.5 (#80), Qwen3 32B: 40.0 (#112)

BenchmarkGPT-5 MiniQwen3 32B
GPQA Diamond75%65.7%
Vectara Hallucination Rate12.9%5.9%
LMArena Expert13771362
Humanity's Last Exam19.4%—
SimpleQA Verified21.6%—
MMLU-Pro83.5%—
Confabulations13.3%—
GPQA (HELM)75.6%—

Multimodal Not comparable

GPT-5 Mini: 35.0 (#80), Qwen3 32B: —

BenchmarkGPT-5 MiniQwen3 32B
LMArena Vision1202—
VPCT40.2%—

Multilingual GPT-5 Mini leads

GPT-5 Mini: 49.1 (#131), Qwen3 32B: 45.8 (#162)

BenchmarkGPT-5 MiniQwen3 32B
LMArena Non-English13631317
LMArena Chinese13871357
LMArena German13661341
LMArena Russian13621311
LMArena French1385—
LMArena Japanese1342—
LMArena Korean1306—
LMArena Spanish1355—

Instruction Following GPT-5 Mini leads

GPT-5 Mini: 76.4 (#43), Qwen3 32B: 69.1 (#174)

BenchmarkGPT-5 MiniQwen3 32B
LMArena Instruction Following13571305
IFEval92.7%—

Long Context Qwen3 32B leads

GPT-5 Mini: 41.9 (#127), Qwen3 32B: 43.7 (#83)

BenchmarkGPT-5 MiniQwen3 32B
Fiction.LiveBench69.4%74.2%
LMArena Longer Query13551327

Writing & Preference GPT-5 Mini leads

GPT-5 Mini: 55.4 (#143), Qwen3 32B: 53.1 (#158)

BenchmarkGPT-5 MiniQwen3 32B
LMArena Text13731340
LMArena Creative Writing13251297
LMArena Multi-Turn13631331
Short-Story Creative Writing83.1%—
EQ-Bench Creative Writing1313—
WildBench85.5%—

Frequently asked questions

Is GPT-5 Mini better than Qwen3 32B?

GPT-5 Mini is the stronger model overall, scoring 41.7 to 38.8 on the Noometry Index.

Which is cheaper, GPT-5 Mini or Qwen3 32B?

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.

Is GPT-5 Mini or Qwen3 32B better for coding?

GPT-5 Mini scores higher on coding benchmarks: 40.0 versus 37.3 in the Noometry coding category.

Which has the bigger context window?

GPT-5 Mini does, with 400K tokens against 131K.

How many benchmarks do GPT-5 Mini and Qwen3 32B share?

25 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Qwen3 32B has 26.

Related comparisons

Go deeper