Noometry

Model comparison

GPT-5.6 Luna vs Kimi K2.7 Code

GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 43.0 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-5.6 Luna OpenAI

54.7

Rank #24 Confirmed

Kimi K2.7 Code Moonshot AI

43.0

Rank #90 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-5.6 Luna scores higher in 5 categories and Kimi K2.7 Code in 0 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Luna leads 77.5 to 52.6.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 61% for GPT-5.6 Luna and 12.2% for Kimi K2.7 Code.
  • GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
  • GPT-5.6 Luna accepts more context: 1.05M tokens versus 262K.
  • Kimi K2.7 Code has downloadable open weights; the other is API-only.

Side by side

GPT-5.6 LunaKimi K2.7 Code
ProviderOpenAIMoonshot AI
Noometry Index54.743.0
Released2026-07-092026-06-12
WeightsProprietaryOpen
Context window1.05M262K
Max output128K262K
Input $ / M tokens$0.20$0.95
Output $ / M tokens$1.20$4
Results tracked5119

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), Kimi K2.7 Code: 42.4 (#92)

BenchmarkGPT-5.6 LunaKimi K2.7 Code
DeepSWE67.2%30.5%
FrontierCode39.8%30.1%
LMArena WebDev15171473
SciCode53.6%47.5%
WeirdML60.9%54.1%
ALE-Bench1,667886.23
CursorBench35.9%—
LMArena Coding1466—

Agentic & Tool Use GPT-5.6 Luna leads

GPT-5.6 Luna: 35.3 (#37), Kimi K2.7 Code: 23.9 (#115)

BenchmarkGPT-5.6 LunaKimi K2.7 Code
Vending-Bench 24,0955,083
APEX-Agents—37.6%
BALROG45.6%—
GBAEval—0.9%
GDP.pdf22.7%—

Reasoning GPT-5.6 Luna leads

GPT-5.6 Luna: 47.5 (#38), Kimi K2.7 Code: 38.2 (#56)

BenchmarkGPT-5.6 LunaKimi K2.7 Code
SimpleBench46.8%57.9%
CritPt20.6%10%
Chess Puzzles40%21%
Surface Evolver Bench61.9%48.8%
Epoch Capabilities Index156.32150.01
ARC-AGI-259.5%—
Kagi LLM Benchmark49.1%—
NYT Connections (extended)69.4%—
ARC-AGI-188%—
LMArena Hard Prompts1452—
Mystery Game Puzzles21%—
DTBench89.1%—
LMCA48.5%—

Math GPT-5.6 Luna leads

GPT-5.6 Luna: 77.5 (#12), Kimi K2.7 Code: 52.6 (#39)

BenchmarkGPT-5.6 LunaKimi K2.7 Code
FrontierMath (Tiers 1-3)82.1%54%
FrontierMath Tier 461%12.2%
OTIS Mock AIME 2024-202598.3%95.6%
ProofBench60%—
LMArena Math1455—

Knowledge GPT-5.6 Luna leads

GPT-5.6 Luna: 58.6 (#31), Kimi K2.7 Code: 53.6 (#51)

BenchmarkGPT-5.6 LunaKimi K2.7 Code
GPQA Diamond91.6%87.9%
SimpleQA Verified41%36.5%
LMArena Expert1479—

Multimodal Not comparable

GPT-5.6 Luna: 43.0 (#22), Kimi K2.7 Code: —

BenchmarkGPT-5.6 LunaKimi K2.7 Code
LMArena Vision1259—
Blueprint-Bench 222.6%—
Furniture Assembly42.5%—
LMArena Document1457—

Multilingual Not comparable

GPT-5.6 Luna: 53.0 (#73), Kimi K2.7 Code: —

BenchmarkGPT-5.6 LunaKimi K2.7 Code
LMArena Non-English1418—
LMArena Chinese1469—
LMArena French1457—
LMArena German1459—
LMArena Japanese1416—
LMArena Korean1414—
LMArena Russian1428—
LMArena Spanish1445—

Instruction Following Not comparable

GPT-5.6 Luna: 76.0 (#48), Kimi K2.7 Code: —

BenchmarkGPT-5.6 LunaKimi K2.7 Code
LMArena Instruction Following1440—

Long Context Not comparable

GPT-5.6 Luna: 43.9 (#78), Kimi K2.7 Code: —

BenchmarkGPT-5.6 LunaKimi K2.7 Code
LMArena Longer Query1437—

Writing & Preference Not comparable

GPT-5.6 Luna: 68.3 (#27), Kimi K2.7 Code: —

BenchmarkGPT-5.6 LunaKimi K2.7 Code
LMArena Text1432—
LMArena Creative Writing1397—
EQ-Bench Creative Writing1829—
EQ-Bench 41156—
LMArena Multi-Turn1433—

Frequently asked questions

Is GPT-5.6 Luna better than Kimi K2.7 Code?

GPT-5.6 Luna is the stronger model overall, scoring 54.7 to 43.0 on the Noometry Index.

Which is cheaper, GPT-5.6 Luna or Kimi K2.7 Code?

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.

Is GPT-5.6 Luna or Kimi K2.7 Code 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 Kimi K2.7 Code share?

17 benchmarks have published results for both models. GPT-5.6 Luna has 51 scored results on Noometry and Kimi K2.7 Code has 19.

Related comparisons

Go deeper