Noometry

Model comparison

GPT-6 Luna vs Qwen2-72B

GPT-6 Luna is the stronger model overall, scoring 53.3 to 30.0 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-6 Luna scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 30.2.
  • The biggest single-benchmark swing is GPQA Diamond: 90.5% for GPT-6 Luna and 40.8% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaQwen2-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index53.330.0
Released2026-09-222024-06-07
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.50—
Results tracked4226

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), Qwen2-72B: 29.1 (#310)

BenchmarkGPT-6 LunaQwen2-72B
LMArena Coding14391196
DeepSWE66.6%—
FrontierCode42.4%—
LMArena WebDev1581—
SciCode54.6%—
WeirdML—11.3%
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%
ALE-Bench1,577—

Agentic & Tool Use GPT-6 Luna leads

GPT-6 Luna: 33.3 (#54), Qwen2-72B: 17.0 (#146)

BenchmarkGPT-6 LunaQwen2-72B
APEX-Agents44.3%—
TheAgentCompany—1.1%
GDP.pdf23%—
METR Time Horizons—29.9%

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Qwen2-72B: 23.2 (#181)

BenchmarkGPT-6 LunaQwen2-72B
LMArena Hard Prompts14111191
Epoch Capabilities Index156.28125.28
ARC-AGI-259.3%—
NYT Connections (extended)68.7%—
ARC-AGI-186.7%—
CritPt19.4%—
Chess Puzzles31%—
Mystery Game Puzzles7%—
DTBench90.1%—
LMCA44.5%—

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Qwen2-72B: 30.2 (#236)

BenchmarkGPT-6 LunaQwen2-72B
LMArena Math14161235
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
OTIS Mock AIME 2024-202598.9%—
ProofBench64%—
MATH Level 5—39.1%

Knowledge GPT-6 Luna leads

GPT-6 Luna: 57.0 (#41), Qwen2-72B: 21.2 (#275)

BenchmarkGPT-6 LunaQwen2-72B
GPQA Diamond90.5%40.8%
LMArena Expert14441171
SimpleQA Verified41.4%—
MMLU—82.4%

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Qwen2-72B: —

BenchmarkGPT-6 LunaQwen2-72B
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 50.5 (#117), Qwen2-72B: 35.9 (#244)

BenchmarkGPT-6 LunaQwen2-72B
LMArena Non-English13861176
LMArena Chinese14331240
LMArena French14201170
LMArena German13691151
LMArena Japanese13691111
LMArena Korean13601083
LMArena Russian13941169
LMArena Spanish13931169

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.3 (#99), Qwen2-72B: 61.7 (#241)

BenchmarkGPT-6 LunaQwen2-72B
LMArena Instruction Following14091181

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.0 (#111), Qwen2-72B: 36.1 (#235)

BenchmarkGPT-6 LunaQwen2-72B
LMArena Longer Query14091192

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), Qwen2-72B: 40.8 (#241)

BenchmarkGPT-6 LunaQwen2-72B
LMArena Text13911203
LMArena Creative Writing13631181
LMArena Multi-Turn13961196

Frequently asked questions

Is GPT-6 Luna better than Qwen2-72B?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 30.0 on the Noometry Index.

Is GPT-6 Luna or Qwen2-72B better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 29.1 in the Noometry coding category.

How many benchmarks do GPT-6 Luna and Qwen2-72B share?

19 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper