Noometry

Model comparison

GPT-4.1 mini vs QwQ-32B

QwQ-32B is the stronger model overall, scoring 39.8 to 33.6 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

QwQ-32B Alibaba (Qwen)

39.8

Rank #159 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-4.1 mini scores higher in 2 categories and QwQ-32B in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in long context, where QwQ-32B leads 49.0 to 31.8.
  • The biggest single-benchmark swing is Fiction.LiveBench: 44.4% for GPT-4.1 mini and 83.3% for QwQ-32B.
  • QwQ-32B has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniQwQ-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index33.639.8
Released2025-04-142024-11-28
WeightsProprietaryOpen
Context window1.05M—
Max output33K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked4736

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

Category by category

Coding QwQ-32B leads

GPT-4.1 mini: 30.6 (#293), QwQ-32B: 35.4 (#226)

BenchmarkGPT-4.1 miniQwQ-32B
Aider Polyglot32.4%20.9%
BigCodeBench Instruct48.9%44.6%
LMArena Coding13671333
SWE-bench Verified (bash only)23.9%—
SciCode40.4%—
WeirdML37.6%—
LiveBench Coding—72.2%
BigCodeBench Complete—54.4%
CadEval16%—

Agentic & Tool Use Not comparable

GPT-4.1 mini: 33.3 (#55), QwQ-32B: —

BenchmarkGPT-4.1 miniQwQ-32B
Berkeley Function Calling Leaderboard50.5%—

Reasoning QwQ-32B leads

GPT-4.1 mini: 10.8 (#340), QwQ-32B: 23.7 (#174)

BenchmarkGPT-4.1 miniQwQ-32B
Chess Puzzles7%5%
LMArena Hard Prompts13491325
Epoch Capabilities Index135.01137.6
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—
CritPt0%—
LiveBench Reasoning—83.5%
Mystery Game Puzzles7%—
DTBench68.8%—
LiveBench Data Analysis—65%
LMCA21.1%—
ForecastBench—58.3
LiveBench—72%

Math QwQ-32B leads

GPT-4.1 mini: 24.1 (#270), QwQ-32B: 38.0 (#143)

BenchmarkGPT-4.1 miniQwQ-32B
OTIS Mock AIME 2024-202544.7%59.2%
LMArena Math13431359
FrontierMath (Tiers 1-3)6.7%—
Omni-MATH49.1%—
LiveBench Math—77.8%
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge QwQ-32B leads

GPT-4.1 mini: 34.7 (#194), QwQ-32B: 37.2 (#158)

BenchmarkGPT-4.1 miniQwQ-32B
GPQA Diamond65.8%65.3%
LMArena Expert13381324
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
Confabulations—15.6%
GPQA (HELM)61.4%—

Multimodal Not comparable

GPT-4.1 mini: 35.8 (#82), QwQ-32B: —

BenchmarkGPT-4.1 miniQwQ-32B
LMArena Vision1181—

Multilingual Too close to call

GPT-4.1 mini: 45.7 (#166), QwQ-32B: 44.8 (#176)

BenchmarkGPT-4.1 miniQwQ-32B
LMArena Non-English13181305
LMArena Chinese13291378
LMArena French13581336
LMArena German13511313
LMArena Japanese12901262
LMArena Korean12981279
LMArena Russian13241297
LMArena Spanish13191354

Instruction Following GPT-4.1 mini leads

GPT-4.1 mini: 73.7 (#118), QwQ-32B: 72.6 (#137)

BenchmarkGPT-4.1 miniQwQ-32B
LMArena Instruction Following13331297
LiveBench Instruction Following—81.8%
IFEval90.4%—

Long Context QwQ-32B leads

GPT-4.1 mini: 31.8 (#275), QwQ-32B: 49.0 (#11)

BenchmarkGPT-4.1 miniQwQ-32B
Fiction.LiveBench44.4%83.3%
LMArena Longer Query13441308

Writing & Preference QwQ-32B leads

GPT-4.1 mini: 48.6 (#199), QwQ-32B: 50.6 (#180)

BenchmarkGPT-4.1 miniQwQ-32B
LMArena Text13401329
LMArena Creative Writing13001288
EQ-Bench Creative Writing11471257
LMArena Multi-Turn13541314
Short-Story Creative Writing—80.2%
WildBench83.8%—
LiveBench Language—51.4%

Frequently asked questions

Is GPT-4.1 mini better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.8 to 33.6 on the Noometry Index.

Is GPT-4.1 mini or QwQ-32B better for coding?

QwQ-32B scores higher on coding benchmarks: 35.4 versus 30.6 in the Noometry coding category.

How many benchmarks do GPT-4.1 mini and QwQ-32B share?

25 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper