Noometry

Model comparison

o3-mini vs QwQ-32B

QwQ-32B is the stronger model overall, scoring 39.4 to 36.7 on the Noometry Index.

Last verified . 33 shared benchmarks.

o3-mini OpenAI

36.7

Rank #205 Confirmed

QwQ-32B Alibaba (Qwen)

39.4

Rank #153 Confirmed

Summary

  • They share 33 benchmarks with published results for both. o3-mini scores higher in 4 categories and QwQ-32B in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in long context, where QwQ-32B leads 49.0 to 33.8.
  • The biggest single-benchmark swing is Aider Polyglot: 60.4% for o3-mini and 20.9% for QwQ-32B.
  • QwQ-32B has downloadable open weights; the other is API-only.

Side by side

o3-miniQwQ-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index36.739.4
Released2024-12-202024-11-28
WeightsProprietaryOpen
Context window200K—
Max output100K—
Input $ / M tokens$1.10—
Output $ / M tokens$4.40—
Results tracked5136

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

Category by category

Coding o3-mini leads

o3-mini: 41.4 (#116), QwQ-32B: 34.9 (#220)

Benchmarko3-miniQwQ-32B
Aider Polyglot60.4%20.9%
LiveBench Coding82.7%72.2%
LMArena Coding13781333
SciCode39.8%—
GSO1.3%—
WeirdML43.7%—
BigCodeBench Instruct—44.6%
BigCodeBench Complete—54.4%
CadEval54%—

Agentic & Tool Use Not comparable

o3-mini: 29.3 (#79), QwQ-32B: —

Benchmarko3-miniQwQ-32B
Cybench22.5%—

Reasoning QwQ-32B leads

o3-mini: 16.3 (#295), QwQ-32B: 22.9 (#171)

Benchmarko3-miniQwQ-32B
Chess Puzzles17%5%
LiveBench Reasoning89.6%83.5%
LMArena Hard Prompts13661326
LiveBench Data Analysis70.6%65%
Epoch Capabilities Index140.35137.6
ForecastBench59.658.3
LiveBench75.9%72%
ARC-AGI-23%—
SimpleBench22.8%—
ARC-AGI-134.5%—
CritPt0.3%—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA19%—

Math QwQ-32B leads

o3-mini: 27.6 (#236), QwQ-32B: 36.2 (#123)

Benchmarko3-miniQwQ-32B
OTIS Mock AIME 2024-202576.9%59.2%
LiveBench Math77.3%77.8%
LMArena Math13961359
FrontierMath (Tiers 1-3)18.6%—
FrontierMath Tier 40%—
MATH Level 596.5%—
FrontierMath (Feb 2025 set)12.4%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge o3-mini leads

o3-mini: 38.3 (#135), QwQ-32B: 37.2 (#150)

Benchmarko3-miniQwQ-32B
GPQA Diamond77%65.3%
Confabulations17.9%15.6%
LMArena Expert13641323
SimpleQA Verified15.3%—

Multilingual Too close to call

o3-mini: 45.9 (#159), QwQ-32B: 45.0 (#171)

Benchmarko3-miniQwQ-32B
LMArena Non-English13191306
LMArena Chinese13791378
LMArena French13331337
LMArena German13031313
LMArena Japanese12861263
LMArena Korean13141278
LMArena Russian13041297
LMArena Spanish13211353

Instruction Following o3-mini leads

o3-mini: 75.3 (#67), QwQ-32B: 72.8 (#131)

Benchmarko3-miniQwQ-32B
LiveBench Instruction Following84.4%81.8%
LMArena Instruction Following13381297

Long Context QwQ-32B leads

o3-mini: 33.8 (#251), QwQ-32B: 49.0 (#11)

Benchmarko3-miniQwQ-32B
Fiction.LiveBench50%83.3%
LMArena Longer Query13431308

Writing & Preference Too close to call

o3-mini: 50.4 (#177), QwQ-32B: 50.9 (#175)

Benchmarko3-miniQwQ-32B
LMArena Text13371329
LMArena Creative Writing12861288
Short-Story Creative Writing61.7%80.2%
LMArena Multi-Turn13201314
LiveBench Language50.7%51.4%
EQ-Bench Creative Writing—1257

Frequently asked questions

Is o3-mini better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.4 to 36.7 on the Noometry Index.

Is o3-mini or QwQ-32B better for coding?

o3-mini scores higher on coding benchmarks: 41.4 versus 34.9 in the Noometry coding category.

How many benchmarks do o3-mini and QwQ-32B share?

33 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper