Noometry

Model comparison

GPT-6 Luna vs Qwen2.5-Max

GPT-6 Luna is the stronger model overall, scoring 53.3 to 40.7 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-6 Luna scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 36.9.

Side by side

GPT-6 LunaQwen2.5-Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index53.340.7
Released2026-09-222025-01-25
WeightsProprietaryProprietary
Context window1.05M—
Max output128K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.50—
Results tracked4227

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), Qwen2.5-Max: 41.8 (#117)

BenchmarkGPT-6 LunaQwen2.5-Max
LMArena Coding14391359
DeepSWE66.6%—
FrontierCode42.4%—
LMArena WebDev1581—
SciCode54.6%—
LiveBench Coding—64.4%
ALE-Bench1,577—

Agentic & Tool Use Not comparable

GPT-6 Luna: 33.3 (#54), Qwen2.5-Max: —

BenchmarkGPT-6 LunaQwen2.5-Max
APEX-Agents44.3%—
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Qwen2.5-Max: 25.6 (#147)

BenchmarkGPT-6 LunaQwen2.5-Max
LMArena Hard Prompts14111360
Epoch Capabilities Index156.28132.53
ARC-AGI-259.3%—
NYT Connections (extended)68.7%—
ARC-AGI-186.7%—
CritPt19.4%—
Chess Puzzles31%—
LiveBench Reasoning—51.4%
Mystery Game Puzzles7%—
DTBench90.1%—
LiveBench Data Analysis—67.9%
LMCA44.5%—
LiveBench—62.3%

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Qwen2.5-Max: 36.9 (#162)

BenchmarkGPT-6 LunaQwen2.5-Max
LMArena Math14161369
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
OTIS Mock AIME 2024-202598.9%—
ProofBench64%—
LiveBench Math—58.4%

Knowledge GPT-6 Luna leads

GPT-6 Luna: 57.0 (#41), Qwen2.5-Max: 35.3 (#186)

BenchmarkGPT-6 LunaQwen2.5-Max
LMArena Expert14441337
GPQA Diamond90.5%—
SimpleQA Verified41.4%—
Confabulations—21.8%

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Qwen2.5-Max: —

BenchmarkGPT-6 LunaQwen2.5-Max
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 50.5 (#117), Qwen2.5-Max: 48.1 (#146)

BenchmarkGPT-6 LunaQwen2.5-Max
LMArena Non-English13861352
LMArena Chinese14331382
LMArena French14201396
LMArena German13691350
LMArena Japanese13691300
LMArena Korean13601304
LMArena Russian13941353
LMArena Spanish13931377

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.3 (#99), Qwen2.5-Max: 71.3 (#152)

BenchmarkGPT-6 LunaQwen2.5-Max
LMArena Instruction Following14091335
LiveBench Instruction Following—75.3%

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.0 (#111), Qwen2.5-Max: 41.4 (#142)

BenchmarkGPT-6 LunaQwen2.5-Max
LMArena Longer Query14091358

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), Qwen2.5-Max: 55.4 (#146)

BenchmarkGPT-6 LunaQwen2.5-Max
LMArena Text13911367
LMArena Creative Writing13631339
LMArena Multi-Turn13961364
Short-Story Creative Writing—72.9%
LiveBench Language—56.3%

Frequently asked questions

Is GPT-6 Luna better than Qwen2.5-Max?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 40.7 on the Noometry Index.

Is GPT-6 Luna or Qwen2.5-Max better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 41.8 in the Noometry coding category.

How many benchmarks do GPT-6 Luna and Qwen2.5-Max share?

18 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper