Noometry

Model comparison

o4-mini vs QwQ-32B

o4-mini is the stronger model overall, scoring 41.6 to 39.8 on the Noometry Index.

Last verified . 26 shared benchmarks.

o4-mini OpenAI

41.6

Rank #132 Confirmed

QwQ-32B Alibaba (Qwen)

39.8

Rank #159 Confirmed

Summary

  • They share 26 benchmarks with published results for both. o4-mini scores higher in 7 categories and QwQ-32B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where o4-mini leads 43.6 to 37.2.
  • The biggest single-benchmark swing is Aider Polyglot: 72% for o4-mini and 20.9% for QwQ-32B.
  • QwQ-32B has downloadable open weights; the other is API-only.

Side by side

o4-miniQwQ-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index41.639.8
Released2025-04-162024-11-28
WeightsProprietaryOpen
Context window200K—
Max output100K—
Input $ / M tokens$1.10—
Output $ / M tokens$4.40—
Results tracked6036

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

Category by category

Coding o4-mini leads

o4-mini: 40.9 (#127), QwQ-32B: 35.4 (#226)

Benchmarko4-miniQwQ-32B
Aider Polyglot72%20.9%
LMArena Coding13681333
SWE-bench Verified (bash only)45%—
GSO3.6%—
WeirdML52.6%—
BigCodeBench Instruct—44.6%
LiveBench Coding—72.2%
BigCodeBench Complete—54.4%
CadEval62%—
ALE-Bench826.17—
AlgoTune1.72—

Agentic & Tool Use Not comparable

o4-mini: 32.6 (#61), QwQ-32B: —

Benchmarko4-miniQwQ-32B
Berkeley Function Calling Leaderboard53.2%—
GDPval25.3%—
METR Time Horizons63.9%—

Reasoning Too close to call

o4-mini: 24.6 (#162), QwQ-32B: 23.7 (#174)

Benchmarko4-miniQwQ-32B
Chess Puzzles26%5%
LMArena Hard Prompts13511325
Epoch Capabilities Index145.64137.6
ForecastBench61.858.3
ARC-AGI-26.1%—
SimpleBench38.7%—
Kagi LLM Benchmark67.6%—
ARC-AGI-158.7%—
CritPt0.6%—
EnigmaEval9.2%—
LiveBench Reasoning—83.5%
Mystery Game Puzzles5%—
DTBench77.6%—
LiveBench Data Analysis—65%
LMCA26.5%—
LiveBench—72%

Math o4-mini leads

o4-mini: 40.8 (#89), QwQ-32B: 38.0 (#143)

Benchmarko4-miniQwQ-32B
OTIS Mock AIME 2024-202581.7%59.2%
LMArena Math13891359
FrontierMath (Tiers 1-3)36.1%—
FrontierMath Tier 44.9%—
Omni-MATH72%—
LiveBench Math—77.8%
MATH Level 597.8%—
FrontierMath (Feb 2025 set)24.8%—
FrontierMath Tier 4 (v1)6.3%—

Knowledge o4-mini leads

o4-mini: 43.6 (#91), QwQ-32B: 37.2 (#158)

Benchmarko4-miniQwQ-32B
GPQA Diamond79.6%65.3%
Confabulations15.8%15.6%
LMArena Expert13431324
Humanity's Last Exam18.1%—
SimpleQA Verified19.6%—
MMLU-Pro82%—
Vectara Hallucination Rate18.6%—
GPQA (HELM)73.5%—

Multimodal Not comparable

o4-mini: 40.2 (#49), QwQ-32B: —

Benchmarko4-miniQwQ-32B
LMArena Vision1194—
GeoBench64%—
VPCT57.5%—

Multilingual o4-mini leads

o4-mini: 47.0 (#154), QwQ-32B: 44.8 (#176)

Benchmarko4-miniQwQ-32B
LMArena Non-English13371305
LMArena Chinese13541378
LMArena French13641336
LMArena German13361313
LMArena Japanese13081262
LMArena Korean13121279
LMArena Russian13341297
LMArena Spanish13471354

Instruction Following o4-mini leads

o4-mini: 75.2 (#68), QwQ-32B: 72.6 (#137)

Benchmarko4-miniQwQ-32B
LMArena Instruction Following13211297
LiveBench Instruction Following—81.8%
IFEval92.8%—

Long Context QwQ-32B leads

o4-mini: 45.5 (#33), QwQ-32B: 49.0 (#11)

Benchmarko4-miniQwQ-32B
Fiction.LiveBench77.8%83.3%
LMArena Longer Query13151308

Writing & Preference o4-mini leads

o4-mini: 54.0 (#152), QwQ-32B: 50.6 (#180)

Benchmarko4-miniQwQ-32B
LMArena Text13531329
LMArena Creative Writing12941288
Short-Story Creative Writing75%80.2%
LMArena Multi-Turn13501314
EQ-Bench Creative Writing—1257
WildBench85.4%—
LiveBench Language—51.4%

Frequently asked questions

Is o4-mini better than QwQ-32B?

o4-mini is the stronger model overall, scoring 41.6 to 39.8 on the Noometry Index.

Is o4-mini or QwQ-32B better for coding?

o4-mini scores higher on coding benchmarks: 40.9 versus 35.4 in the Noometry coding category.

How many benchmarks do o4-mini and QwQ-32B share?

26 benchmarks have published results for both models. o4-mini has 60 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper