Noometry

Model comparison

GPT-5.6 Luna vs Qwen3.7 Max

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 51.5 on the Noometry Index.

Last verified . 30 shared benchmarks.

GPT-5.6 Luna OpenAI

54.6

Rank #30 Confirmed

Qwen3.7 Max Alibaba (Qwen)

51.5

Rank #42 Confirmed

Summary

  • They share 30 benchmarks with published results for both. GPT-5.6 Luna scores higher in 4 categories and Qwen3.7 Max in 5 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 62.4.
  • The biggest single-benchmark swing is ProofBench: 60% for GPT-5.6 Luna and 26% for Qwen3.7 Max.
  • GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
  • GPT-5.6 Luna accepts more context: 1.05M tokens versus 1M.

Side by side

GPT-5.6 LunaQwen3.7 Max
ProviderOpenAIAlibaba (Qwen)
Noometry Index54.651.5
Released2026-07-092026-05-19
WeightsProprietaryProprietary
Context window1.05M1M
Max output128K131K
Input $ / M tokens$0.20$2.50
Output $ / M tokens$1.20$7.50
Results tracked5233

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 Max: 50.4 (#45)

BenchmarkGPT-5.6 LunaQwen3.7 Max
LMArena WebDev15191515
SciCode53.6%48.8%
LMArena Coding14661498
ALE-Bench1,6671,189
SWE-bench Verified—77.3%
DeepSWE67.2%—
FrontierCode39.8%—
CursorBench35.9%—
WeirdML60.9%—

Agentic & Tool Use GPT-5.6 Luna leads

GPT-5.6 Luna: 34.4 (#45), Qwen3.7 Max: 22.1 (#135)

BenchmarkGPT-5.6 LunaQwen3.7 Max
APEX-Agents43%—
BALROG45.6%—
GBAEval—0.4%
GDP.pdf22.7%—
Vending-Bench 24,095—

Reasoning Qwen3.7 Max leads

GPT-5.6 Luna: 47.6 (#43), Qwen3.7 Max: 49.2 (#38)

BenchmarkGPT-5.6 LunaQwen3.7 Max
SimpleBench46.8%70.4%
NYT Connections (extended)69.4%85.1%
CritPt20.6%13.4%
Chess Puzzles40%19%
LMArena Hard Prompts14511483
Mystery Game Puzzles21%32%
DTBench89.1%92.3%
LMCA48.5%44%
Epoch Capabilities Index156.39153.68
ARC-AGI-259.5%—
Kagi LLM Benchmark49.1%—
ARC-AGI-188%—
EBR-Bench—9.5%
Surface Evolver Bench61.9%—

Math GPT-5.6 Luna leads

GPT-5.6 Luna: 77.7 (#14), Qwen3.7 Max: 62.4 (#32)

BenchmarkGPT-5.6 LunaQwen3.7 Max
FrontierMath (Tiers 1-3)82.1%64.6%
FrontierMath Tier 461%34.1%
OTIS Mock AIME 2024-202598.3%95.6%
ProofBench60%26%
LMArena Math14581490

Knowledge Qwen3.7 Max leads

GPT-5.6 Luna: 58.5 (#34), Qwen3.7 Max: 61.6 (#28)

BenchmarkGPT-5.6 LunaQwen3.7 Max
GPQA Diamond91.6%90.9%
SimpleQA Verified41%55.8%
LMArena Expert14781488

Multimodal Not comparable

GPT-5.6 Luna: 42.7 (#28), Qwen3.7 Max: —

BenchmarkGPT-5.6 LunaQwen3.7 Max
LMArena Vision1258—
Blueprint-Bench 222.6%—
Furniture Assembly42.5%—
LMArena Document1457—

Multilingual Qwen3.7 Max leads

GPT-5.6 Luna: 52.8 (#78), Qwen3.7 Max: 56.9 (#15)

BenchmarkGPT-5.6 LunaQwen3.7 Max
LMArena Non-English14171474
LMArena Chinese14701530
LMArena Russian14281484
LMArena French1456—
LMArena German1454—
LMArena Japanese1411—
LMArena Korean1415—
LMArena Spanish1448—

Instruction Following Qwen3.7 Max leads

GPT-5.6 Luna: 75.6 (#57), Qwen3.7 Max: 76.7 (#38)

BenchmarkGPT-5.6 LunaQwen3.7 Max
LMArena Instruction Following14371460

Long Context Qwen3.7 Max leads

GPT-5.6 Luna: 43.9 (#82), Qwen3.7 Max: 45.4 (#40)

BenchmarkGPT-5.6 LunaQwen3.7 Max
LMArena Longer Query14361482

Writing & Preference GPT-5.6 Luna leads

GPT-5.6 Luna: 68.0 (#29), Qwen3.7 Max: 65.0 (#54)

BenchmarkGPT-5.6 LunaQwen3.7 Max
LMArena Text14311476
LMArena Creative Writing13961449
EQ-Bench 411561110
LMArena Multi-Turn14341481
EQ-Bench Creative Writing1829—

Frequently asked questions

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

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 51.5 on the Noometry Index.

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

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.

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

GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 50.4 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 Max share?

30 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Qwen3.7 Max has 33.

Related comparisons

Go deeper