Noometry

Model comparison

Command A vs GPT-5.6 Luna

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 36.5 on the Noometry Index.

Last verified . 21 shared benchmarks.

Command A Cohere

36.5

Rank #215 Confirmed

GPT-5.6 Luna OpenAI

54.6

Rank #30 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Command A scores higher in 1 category and GPT-5.6 Luna in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 36.2.
  • The biggest single-benchmark swing is LMCA: 10.3% for Command A and 48.5% for GPT-5.6 Luna.
  • GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $2.50 / $10 for Command A.
  • GPT-5.6 Luna accepts more context: 1.05M tokens versus 256K.
  • Command A has downloadable open weights; the other is API-only.

Side by side

Command AGPT-5.6 Luna
ProviderCohereOpenAI
Noometry Index36.554.6
Released2025-03-132026-07-09
WeightsOpenProprietary
Context window256K1.05M
Max output8K128K
Input $ / M tokens$2.50$0.20
Output $ / M tokens$10$1.20
Results tracked2452

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

Category by category

Coding GPT-5.6 Luna leads

Command A: 27.2 (#322), GPT-5.6 Luna: 54.5 (#28)

BenchmarkCommand AGPT-5.6 Luna
LMArena Coding13301466
DeepSWE—67.2%
FrontierCode—39.8%
Aider Polyglot12%—
CursorBench—35.9%
LMArena WebDev—1519
SciCode—53.6%
WeirdML—60.9%
ALE-Bench—1,667

Agentic & Tool Use Command A leads

Command A: 35.9 (#40), GPT-5.6 Luna: 34.4 (#45)

BenchmarkCommand AGPT-5.6 Luna
APEX-Agents—43%
Berkeley Function Calling Leaderboard57.1%—
BALROG—45.6%
GDP.pdf—22.7%
Vending-Bench 2—4,095

Reasoning GPT-5.6 Luna leads

Command A: 18.3 (#283), GPT-5.6 Luna: 47.6 (#43)

BenchmarkCommand AGPT-5.6 Luna
Kagi LLM Benchmark28.8%49.1%
LMArena Hard Prompts13261451
DTBench61.3%89.1%
LMCA10.3%48.5%
ARC-AGI-2—59.5%
SimpleBench—46.8%
NYT Connections (extended)—69.4%
ARC-AGI-1—88%
CritPt—20.6%
Chess Puzzles—40%
Mystery Game Puzzles—21%
Surface Evolver Bench—61.9%
Epoch Capabilities Index—156.39

Math GPT-5.6 Luna leads

Command A: 36.2 (#171), GPT-5.6 Luna: 77.7 (#14)

BenchmarkCommand AGPT-5.6 Luna
LMArena Math13001458
FrontierMath (Tiers 1-3)—82.1%
FrontierMath Tier 4—61%
OTIS Mock AIME 2024-2025—98.3%
ProofBench—60%

Knowledge GPT-5.6 Luna leads

Command A: 37.1 (#159), GPT-5.6 Luna: 58.5 (#34)

BenchmarkCommand AGPT-5.6 Luna
LMArena Expert12951478
GPQA Diamond—91.6%
SimpleQA Verified—41%
Vectara Hallucination Rate9.3%—

Multimodal Not comparable

Command A: —, GPT-5.6 Luna: 42.7 (#28)

BenchmarkCommand AGPT-5.6 Luna
LMArena Vision—1258
Blueprint-Bench 2—22.6%
Furniture Assembly—42.5%
LMArena Document—1457

Multilingual GPT-5.6 Luna leads

Command A: 45.3 (#170), GPT-5.6 Luna: 52.8 (#78)

BenchmarkCommand AGPT-5.6 Luna
LMArena Non-English13131417
LMArena Chinese13271470
LMArena French13511456
LMArena German13411454
LMArena Japanese12851411
LMArena Korean12851415
LMArena Russian13141428
LMArena Spanish13471448

Instruction Following GPT-5.6 Luna leads

Command A: 69.1 (#177), GPT-5.6 Luna: 75.6 (#57)

BenchmarkCommand AGPT-5.6 Luna
LMArena Instruction Following13091437

Long Context GPT-5.6 Luna leads

Command A: 40.6 (#151), GPT-5.6 Luna: 43.9 (#82)

BenchmarkCommand AGPT-5.6 Luna
LMArena Longer Query13341436

Writing & Preference GPT-5.6 Luna leads

Command A: 47.6 (#208), GPT-5.6 Luna: 68.0 (#29)

BenchmarkCommand AGPT-5.6 Luna
LMArena Text13311431
LMArena Creative Writing13191396
EQ-Bench Creative Writing11451829
LMArena Multi-Turn13391434
EQ-Bench 4—1156

Frequently asked questions

Is Command A better than GPT-5.6 Luna?

GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 36.5 on the Noometry Index.

Which is cheaper, Command A or GPT-5.6 Luna?

GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; Command A lists at $2.50 and $10.

Is Command A or GPT-5.6 Luna better for coding?

GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 27.2 in the Noometry coding category.

Which has the bigger context window?

GPT-5.6 Luna does, with 1.05M tokens against 256K.

How many benchmarks do Command A and GPT-5.6 Luna share?

21 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GPT-5.6 Luna has 52.

Related comparisons

Go deeper