Noometry

Model comparison

GPT-5.6 Luna vs Qwen3 Max

GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 43.5 on the Noometry Index.

Last verified . 30 shared benchmarks.

GPT-5.6 Luna OpenAI

54.7

Rank #24 Confirmed

Qwen3 Max Alibaba (Qwen)

43.5

Rank #82 Confirmed

Summary

  • They share 30 benchmarks with published results for both. GPT-5.6 Luna scores higher in 7 categories and Qwen3 Max in 1 category; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Luna leads 77.5 to 37.6.
  • The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 82.1% for GPT-5.6 Luna and 18.9% for Qwen3 Max.
  • GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
  • GPT-5.6 Luna accepts more context: 1.05M tokens versus 262K.

Side by side

GPT-5.6 LunaQwen3 Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index54.743.5
Released2026-07-092025-09-23
WeightsProprietaryProprietary
Context window1.05M262K
Max output128K66K
Input $ / M tokens$0.20$1.20
Output $ / M tokens$1.20$6
Results tracked5133

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

Category by category

Coding GPT-5.6 Luna leads

GPT-5.6 Luna: 53.9 (#25), Qwen3 Max: 42.4 (#93)

BenchmarkGPT-5.6 LunaQwen3 Max
LMArena Coding14661456
ALE-Bench1,667370.45
DeepSWE67.2%—
FrontierCode39.8%—
CursorBench35.9%—
LMArena WebDev1517—
SciCode53.6%—
WeirdML60.9%—

Agentic & Tool Use Not comparable

GPT-5.6 Luna: 35.3 (#37), Qwen3 Max: —

BenchmarkGPT-5.6 LunaQwen3 Max
Vending-Bench 24,09571.56
BALROG45.6%—
GDP.pdf22.7%—

Reasoning GPT-5.6 Luna leads

GPT-5.6 Luna: 47.5 (#38), Qwen3 Max: 22.0 (#186)

BenchmarkGPT-5.6 LunaQwen3 Max
Kagi LLM Benchmark49.1%72.5%
NYT Connections (extended)69.4%30.1%
Chess Puzzles40%4%
LMArena Hard Prompts14521448
Mystery Game Puzzles21%5%
DTBench89.1%82.1%
LMCA48.5%28.3%
Epoch Capabilities Index156.32142.41
ARC-AGI-259.5%—
SimpleBench46.8%—
ARC-AGI-188%—
CritPt20.6%—
Surface Evolver Bench61.9%—

Math GPT-5.6 Luna leads

GPT-5.6 Luna: 77.5 (#12), Qwen3 Max: 37.6 (#94)

BenchmarkGPT-5.6 LunaQwen3 Max
FrontierMath (Tiers 1-3)82.1%18.9%
OTIS Mock AIME 2024-202598.3%73.3%
LMArena Math14551447
FrontierMath Tier 461%—
ProofBench60%—
MATH Level 5—97.1%

Knowledge GPT-5.6 Luna leads

GPT-5.6 Luna: 58.6 (#31), Qwen3 Max: 48.1 (#72)

BenchmarkGPT-5.6 LunaQwen3 Max
GPQA Diamond91.6%72.6%
SimpleQA Verified41%48.7%
LMArena Expert14791457

Multimodal Not comparable

GPT-5.6 Luna: 43.0 (#22), Qwen3 Max: —

BenchmarkGPT-5.6 LunaQwen3 Max
LMArena Vision1259—
Blueprint-Bench 222.6%—
Furniture Assembly42.5%—
LMArena Document1457—

Multilingual Too close to call

GPT-5.6 Luna: 53.0 (#73), Qwen3 Max: 53.9 (#58)

BenchmarkGPT-5.6 LunaQwen3 Max
LMArena Non-English14181429
LMArena Chinese14691479
LMArena French14571450
LMArena German14591463
LMArena Japanese14161399
LMArena Korean14141397
LMArena Russian14281428
LMArena Spanish14451463

Instruction Following Too close to call

GPT-5.6 Luna: 76.0 (#48), Qwen3 Max: 75.0 (#81)

BenchmarkGPT-5.6 LunaQwen3 Max
LMArena Instruction Following14401420

Long Context GPT-5.6 Luna leads

GPT-5.6 Luna: 43.9 (#78), Qwen3 Max: 41.6 (#129)

BenchmarkGPT-5.6 LunaQwen3 Max
LMArena Longer Query14371439
Fiction.LiveBench—66.7%
CL-bench—14.5%

Writing & Preference GPT-5.6 Luna leads

GPT-5.6 Luna: 68.3 (#27), Qwen3 Max: 62.6 (#72)

BenchmarkGPT-5.6 LunaQwen3 Max
LMArena Text14321439
LMArena Creative Writing13971401
LMArena Multi-Turn14331446
EQ-Bench Creative Writing1829—
EQ-Bench 41156—

Frequently asked questions

Is GPT-5.6 Luna better than Qwen3 Max?

GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 43.5 on the Noometry Index.

Which is cheaper, GPT-5.6 Luna or Qwen3 Max?

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Qwen3 Max lists at $1.20 and $6.

Is GPT-5.6 Luna or Qwen3 Max better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 53.9 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

GPT-5.6 Luna does, with 1.05M tokens against 262K.

How many benchmarks do GPT-5.6 Luna and Qwen3 Max share?

30 benchmarks have published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper