Noometry

Model comparison

GPT-6 Luna vs QwQ-32B

GPT-6 Luna is the stronger model overall, scoring 53.3 to 39.8 on the Noometry Index.

Last verified . 21 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

QwQ-32B Alibaba (Qwen)

39.8

Rank #159 Confirmed

Summary

  • They share 21 benchmarks with published results for both. GPT-6 Luna scores higher in 7 categories and QwQ-32B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 38.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for GPT-6 Luna and 59.2% for QwQ-32B.
  • QwQ-32B has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaQwQ-32B
ProviderOpenAIAlibaba (Qwen)
Noometry Index53.339.8
Released2026-09-222024-11-28
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.50—
Results tracked4236

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

Category by category

Coding GPT-6 Luna leads

GPT-6 Luna: 55.5 (#25), QwQ-32B: 35.4 (#226)

BenchmarkGPT-6 LunaQwQ-32B
LMArena Coding14391333
DeepSWE66.6%—
FrontierCode42.4%—
Aider Polyglot—20.9%
LMArena WebDev1581—
SciCode54.6%—
BigCodeBench Instruct—44.6%
LiveBench Coding—72.2%
BigCodeBench Complete—54.4%
ALE-Bench1,577—

Agentic & Tool Use Not comparable

GPT-6 Luna: 33.3 (#54), QwQ-32B: —

BenchmarkGPT-6 LunaQwQ-32B
APEX-Agents44.3%—
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), QwQ-32B: 23.7 (#174)

BenchmarkGPT-6 LunaQwQ-32B
Chess Puzzles31%5%
LMArena Hard Prompts14111325
Epoch Capabilities Index156.28137.6
ARC-AGI-259.3%—
NYT Connections (extended)68.7%—
ARC-AGI-186.7%—
CritPt19.4%—
LiveBench Reasoning—83.5%
Mystery Game Puzzles7%—
DTBench90.1%—
LiveBench Data Analysis—65%
LMCA44.5%—
ForecastBench—58.3
LiveBench—72%

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), QwQ-32B: 38.0 (#143)

BenchmarkGPT-6 LunaQwQ-32B
OTIS Mock AIME 2024-202598.9%59.2%
LMArena Math14161359
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
ProofBench64%—
LiveBench Math—77.8%

Knowledge GPT-6 Luna leads

GPT-6 Luna: 57.0 (#41), QwQ-32B: 37.2 (#158)

BenchmarkGPT-6 LunaQwQ-32B
GPQA Diamond90.5%65.3%
LMArena Expert14441324
SimpleQA Verified41.4%—
Confabulations—15.6%

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), QwQ-32B: —

BenchmarkGPT-6 LunaQwQ-32B
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 50.5 (#117), QwQ-32B: 44.8 (#176)

BenchmarkGPT-6 LunaQwQ-32B
LMArena Non-English13861305
LMArena Chinese14331378
LMArena French14201336
LMArena German13691313
LMArena Japanese13691262
LMArena Korean13601279
LMArena Russian13941297
LMArena Spanish13931354

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.3 (#99), QwQ-32B: 72.6 (#137)

BenchmarkGPT-6 LunaQwQ-32B
LMArena Instruction Following14091297
LiveBench Instruction Following—81.8%

Long Context QwQ-32B leads

GPT-6 Luna: 43.0 (#111), QwQ-32B: 49.0 (#11)

BenchmarkGPT-6 LunaQwQ-32B
LMArena Longer Query14091308
Fiction.LiveBench—83.3%

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), QwQ-32B: 50.6 (#180)

BenchmarkGPT-6 LunaQwQ-32B
LMArena Text13911329
LMArena Creative Writing13631288
LMArena Multi-Turn13961314
Short-Story Creative Writing—80.2%
EQ-Bench Creative Writing—1257
LiveBench Language—51.4%

Frequently asked questions

Is GPT-6 Luna better than QwQ-32B?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 39.8 on the Noometry Index.

Is GPT-6 Luna or QwQ-32B better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 35.4 in the Noometry coding category.

How many benchmarks do GPT-6 Luna and QwQ-32B share?

21 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper