Noometry

Model comparison

GPT-5.6 Luna vs Qwen3.7 Plus

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 45.3 on the Noometry Index.

Last verified . 31 shared benchmarks.

GPT-5.6 Luna OpenAI

54.6

Rank #30 Confirmed

Qwen3.7 Plus Alibaba (Qwen)

45.3

Rank #72 Confirmed

Summary

  • They share 31 benchmarks with published results for both. GPT-5.6 Luna scores higher in 7 categories and Qwen3.7 Plus in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 50.5.
  • The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 82.1% for GPT-5.6 Luna and 34.4% for Qwen3.7 Plus.
  • GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
  • GPT-5.6 Luna accepts more context: 1.05M tokens versus 1M.

Side by side

GPT-5.6 LunaQwen3.7 Plus
ProviderOpenAIAlibaba (Qwen)
Noometry Index54.645.3
Released2026-07-092026-06-02
WeightsProprietaryProprietary
Context window1.05M1M
Max output128K131K
Input $ / M tokens$0.20$0.40
Output $ / M tokens$1.20$1.60
Results tracked5232

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: 54.5 (#28), Qwen3.7 Plus: 36.6 (#206)

BenchmarkGPT-5.6 LunaQwen3.7 Plus
FrontierCode39.8%10.2%
SciCode53.6%45.5%
LMArena Coding14661473
DeepSWE67.2%—
CursorBench35.9%—
LMArena WebDev1519—
WeirdML60.9%—
ALE-Bench1,667—

Agentic & Tool Use GPT-5.6 Luna leads

GPT-5.6 Luna: 34.4 (#45), Qwen3.7 Plus: 21.4 (#138)

BenchmarkGPT-5.6 LunaQwen3.7 Plus
APEX-Agents43%—
OSWorld 2.0—2.8%
BALROG45.6%—
GDP.pdf22.7%—
Vending-Bench 24,095—

Reasoning GPT-5.6 Luna leads

GPT-5.6 Luna: 47.6 (#43), Qwen3.7 Plus: 39.3 (#59)

BenchmarkGPT-5.6 LunaQwen3.7 Plus
NYT Connections (extended)69.4%74.8%
CritPt20.6%9.1%
Chess Puzzles40%24%
LMArena Hard Prompts14511460
Mystery Game Puzzles21%17%
DTBench89.1%84%
LMCA48.5%37.6%
Epoch Capabilities Index156.39147.37
ARC-AGI-259.5%—
SimpleBench46.8%—
Kagi LLM Benchmark49.1%—
ARC-AGI-188%—
Surface Evolver Bench61.9%—

Math GPT-5.6 Luna leads

GPT-5.6 Luna: 77.7 (#14), Qwen3.7 Plus: 50.5 (#56)

BenchmarkGPT-5.6 LunaQwen3.7 Plus
FrontierMath (Tiers 1-3)82.1%34.4%
OTIS Mock AIME 2024-202598.3%93.3%
LMArena Math14581466
FrontierMath Tier 461%—
ProofBench60%—

Knowledge GPT-5.6 Luna leads

GPT-5.6 Luna: 58.5 (#34), Qwen3.7 Plus: 54.9 (#51)

BenchmarkGPT-5.6 LunaQwen3.7 Plus
GPQA Diamond91.6%87.9%
LMArena Expert14781467
SimpleQA Verified41%—

Multimodal Too close to call

GPT-5.6 Luna: 42.7 (#28), Qwen3.7 Plus: 41.8 (#33)

BenchmarkGPT-5.6 LunaQwen3.7 Plus
LMArena Vision12581279
LMArena Document14571444
Blueprint-Bench 222.6%—
Furniture Assembly42.5%—

Multilingual Qwen3.7 Plus leads

GPT-5.6 Luna: 52.8 (#78), Qwen3.7 Plus: 54.8 (#38)

BenchmarkGPT-5.6 LunaQwen3.7 Plus
LMArena Non-English14171445
LMArena Chinese14701510
LMArena French14561473
LMArena German14541471
LMArena Japanese14111413
LMArena Korean14151415
LMArena Russian14281457
LMArena Spanish14481457

Instruction Following Too close to call

GPT-5.6 Luna: 75.6 (#57), Qwen3.7 Plus: 75.8 (#52)

BenchmarkGPT-5.6 LunaQwen3.7 Plus
LMArena Instruction Following14371440

Long Context Too close to call

GPT-5.6 Luna: 43.9 (#82), Qwen3.7 Plus: 44.5 (#65)

BenchmarkGPT-5.6 LunaQwen3.7 Plus
LMArena Longer Query14361455

Writing & Preference GPT-5.6 Luna leads

GPT-5.6 Luna: 68.0 (#29), Qwen3.7 Plus: 64.3 (#56)

BenchmarkGPT-5.6 LunaQwen3.7 Plus
LMArena Text14311455
LMArena Creative Writing13961439
LMArena Multi-Turn14341460
EQ-Bench Creative Writing1829—
EQ-Bench 41156—

Frequently asked questions

Is GPT-5.6 Luna better than Qwen3.7 Plus?

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 45.3 on the Noometry Index.

Which is cheaper, GPT-5.6 Luna or Qwen3.7 Plus?

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.

Is GPT-5.6 Luna or Qwen3.7 Plus better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 36.6 in the Noometry coding category.

Which has the bigger context window?

GPT-5.6 Luna does, with 1.05M tokens against 1M.

How many benchmarks do GPT-5.6 Luna and Qwen3.7 Plus share?

31 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Qwen3.7 Plus has 32.

Related comparisons

Go deeper