Noometry

Model comparison

Command A vs GPT-6 Luna

GPT-6 Luna is the stronger model overall, scoring 45.1 to 35.9 on the Noometry Index.

Last verified . 13 shared benchmarks.

Command A Cohere

35.9

Rank #212 Confirmed

GPT-6 Luna OpenAI

45.1

Rank #65 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Command A scores higher in 0 categories and GPT-6 Luna in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where GPT-6 Luna leads 54.7 to 26.8.
  • GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $2.50 / $10 for Command A.
  • GPT-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-6 Luna
ProviderCohereOpenAI
Noometry Index35.945.1
Released2025-03-132026-09-22
WeightsOpenProprietary
Context window256K1.05M
Max output8K128K
Input $ / M tokens$2.50$0.10
Output $ / M tokens$10$0.50
Results tracked2418

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

Category by category

Coding GPT-6 Luna leads

Command A: 26.8 (#317), GPT-6 Luna: 54.7 (#24)

BenchmarkCommand AGPT-6 Luna
LMArena Coding13311448
DeepSWE—66.6%
FrontierCode—42.4%
Aider Polyglot12%—
LMArena WebDev—1583

Agentic & Tool Use Not comparable

Command A: 35.7 (#36), GPT-6 Luna: —

BenchmarkCommand AGPT-6 Luna
Berkeley Function Calling Leaderboard57.1%—

Reasoning GPT-6 Luna leads

Command A: 17.7 (#276), GPT-6 Luna: 31.7 (#68)

BenchmarkCommand AGPT-6 Luna
LMArena Hard Prompts13261415
Kagi LLM Benchmark28.8%—
NYT Connections (extended)—68.7%
DTBench61.3%—
LMCA10.3%—

Math GPT-6 Luna leads

Command A: 33.5 (#172), GPT-6 Luna: 35.6 (#140)

BenchmarkCommand AGPT-6 Luna
LMArena Math13001396

Knowledge GPT-6 Luna leads

Command A: 36.5 (#157), GPT-6 Luna: 40.1 (#110)

BenchmarkCommand AGPT-6 Luna
LMArena Expert12951458
Vectara Hallucination Rate9.3%—

Multimodal Not comparable

Command A: —, GPT-6 Luna: 42.0 (#27)

BenchmarkCommand AGPT-6 Luna
Furniture Assembly—44.2%

Multilingual GPT-6 Luna leads

Command A: 45.5 (#166), GPT-6 Luna: 51.0 (#111)

BenchmarkCommand AGPT-6 Luna
LMArena Non-English13131390
LMArena Chinese13271425
LMArena Russian13141392
LMArena Spanish13461416
LMArena French1352—
LMArena German1341—
LMArena Japanese1283—
LMArena Korean1285—

Instruction Following GPT-6 Luna leads

Command A: 69.3 (#172), GPT-6 Luna: 74.7 (#85)

BenchmarkCommand AGPT-6 Luna
LMArena Instruction Following13091414

Long Context GPT-6 Luna leads

Command A: 40.6 (#147), GPT-6 Luna: 43.3 (#95)

BenchmarkCommand AGPT-6 Luna
LMArena Longer Query13341417

Writing & Preference GPT-6 Luna leads

Command A: 47.8 (#204), GPT-6 Luna: 58.4 (#115)

BenchmarkCommand AGPT-6 Luna
LMArena Text13311392
LMArena Creative Writing13191357
LMArena Multi-Turn13381400
EQ-Bench Creative Writing1145—

Frequently asked questions

Is Command A better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 35.9 on the Noometry Index.

Which is cheaper, Command A or GPT-6 Luna?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Command A lists at $2.50 and $10.

Is Command A or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 26.8 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 256K.

How many benchmarks do Command A and GPT-6 Luna share?

13 benchmarks have published results for both models. Command A has 24 scored results on Noometry and GPT-6 Luna has 18.

Related comparisons

Go deeper