Noometry

Model comparison

GPT-5.6 Luna vs Inkling

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 44.1 on the Noometry Index.

Last verified . 39 shared benchmarks.

GPT-5.6 Luna OpenAI

54.6

Rank #30 Confirmed

Inkling Thinking Machines Lab

44.1

Rank #80 Confirmed

Summary

  • They share 39 benchmarks with published results for both. GPT-5.6 Luna scores higher in 8 categories and Inkling in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 31.3.
  • The biggest single-benchmark swing is ProofBench: 60% for GPT-5.6 Luna and 0% for Inkling.
  • GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $1.87 / $4.68 for Inkling.
  • GPT-5.6 Luna accepts more context: 1.05M tokens versus 66K.
  • Inkling has downloadable open weights; the other is API-only.

Side by side

GPT-5.6 LunaInkling
ProviderOpenAIThinking Machines Lab
Noometry Index54.644.1
Released2026-07-092026-07-15
WeightsProprietaryOpen
Context window1.05M66K
Max output128K66K
Input $ / M tokens$0.20$1.87
Output $ / M tokens$1.20$4.68
Results tracked5241

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), Inkling: 34.5 (#234)

BenchmarkGPT-5.6 LunaInkling
FrontierCode39.8%14%
LMArena WebDev15191413
SciCode53.6%47%
WeirdML60.9%32.3%
LMArena Coding14661464
ALE-Bench1,667946
DeepSWE67.2%—
CursorBench35.9%—
FrontierSWE—4.1%

Agentic & Tool Use GPT-5.6 Luna leads

GPT-5.6 Luna: 34.4 (#45), Inkling: 29.6 (#85)

BenchmarkGPT-5.6 LunaInkling
APEX-Agents43%33.8%
τ²-bench Banking—25%
BALROG45.6%—
GDP.pdf22.7%—
Vending-Bench 24,095—

Reasoning GPT-5.6 Luna leads

GPT-5.6 Luna: 47.6 (#43), Inkling: 40.4 (#56)

BenchmarkGPT-5.6 LunaInkling
ARC-AGI-259.5%36.5%
SimpleBench46.8%50%
ARC-AGI-188%79.5%
CritPt20.6%5.4%
Chess Puzzles40%21%
LMArena Hard Prompts14511451
DTBench89.1%87.5%
LMCA48.5%37.6%
Epoch Capabilities Index156.39148.54
Kagi LLM Benchmark49.1%—
NYT Connections (extended)69.4%—
Mystery Game Puzzles21%—
Surface Evolver Bench61.9%—

Math GPT-5.6 Luna leads

GPT-5.6 Luna: 77.7 (#14), Inkling: 31.3 (#225)

BenchmarkGPT-5.6 LunaInkling
FrontierMath (Tiers 1-3)82.1%33.3%
FrontierMath Tier 461%4.9%
OTIS Mock AIME 2024-202598.3%88.9%
ProofBench60%0%
LMArena Math14581479

Knowledge GPT-5.6 Luna leads

GPT-5.6 Luna: 58.5 (#34), Inkling: 55.1 (#49)

BenchmarkGPT-5.6 LunaInkling
GPQA Diamond91.6%88.3%
SimpleQA Verified41%40.3%
LMArena Expert14781465

Multimodal Not comparable

GPT-5.6 Luna: 42.7 (#28), Inkling: —

BenchmarkGPT-5.6 LunaInkling
LMArena Vision1258—
Blueprint-Bench 222.6%—
Furniture Assembly42.5%—
LMArena Document1457—

Multilingual Inkling leads

GPT-5.6 Luna: 52.8 (#78), Inkling: 54.0 (#52)

BenchmarkGPT-5.6 LunaInkling
LMArena Non-English14171434
LMArena Chinese14701490
LMArena French14561458
LMArena German14541446
LMArena Japanese14111429
LMArena Korean14151404
LMArena Russian14281429
LMArena Spanish14481448

Instruction Following Too close to call

GPT-5.6 Luna: 75.6 (#57), Inkling: 75.1 (#71)

BenchmarkGPT-5.6 LunaInkling
LMArena Instruction Following14371426

Long Context Too close to call

GPT-5.6 Luna: 43.9 (#82), Inkling: 43.8 (#86)

BenchmarkGPT-5.6 LunaInkling
LMArena Longer Query14361434

Writing & Preference GPT-5.6 Luna leads

GPT-5.6 Luna: 68.0 (#29), Inkling: 65.2 (#51)

BenchmarkGPT-5.6 LunaInkling
LMArena Text14311441
LMArena Creative Writing13961387
EQ-Bench Creative Writing18291611
EQ-Bench 411561226
LMArena Multi-Turn14341436

Frequently asked questions

Is GPT-5.6 Luna better than Inkling?

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 44.1 on the Noometry Index.

Which is cheaper, GPT-5.6 Luna or Inkling?

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Inkling lists at $1.87 and $4.68.

Is GPT-5.6 Luna or Inkling better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 34.5 in the Noometry coding category.

Which has the bigger context window?

GPT-5.6 Luna does, with 1.05M tokens against 66K.

How many benchmarks do GPT-5.6 Luna and Inkling share?

39 benchmarks have published results for both models. GPT-5.6 Luna has 52 scored results on Noometry and Inkling has 41.

Related comparisons

Go deeper