Noometry

Model comparison

Command A vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 36.5 on the Noometry Index.

Last verified . 13 shared benchmarks.

Command A Cohere

36.5

Rank #215 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Command A scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Step 5 Preview leads 51.8 to 27.2.
  • Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $2.50 / $10 for Command A.
  • Step 5 Preview accepts more context: 1.02M tokens versus 256K.
  • Command A has downloadable open weights; the other is API-only.

Side by side

Command AStep 5 Preview
ProviderCohereStepFun
Noometry Index36.547.9
Released2025-03-132026-09-16
WeightsOpenProprietary
Context window256K1.02M
Max output8K66K
Input $ / M tokens$2.50$1
Output $ / M tokens$10$2.70
Results tracked2418

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

Category by category

Coding Step 5 Preview leads

Command A: 27.2 (#322), Step 5 Preview: 51.8 (#36)

BenchmarkCommand AStep 5 Preview
LMArena Coding13301480
Aider Polyglot12%—
LMArena WebDev—1564
SciCode—58.9%

Agentic & Tool Use Not comparable

Command A: 35.9 (#40), Step 5 Preview: —

BenchmarkCommand AStep 5 Preview
Berkeley Function Calling Leaderboard57.1%—

Reasoning Step 5 Preview leads

Command A: 18.3 (#283), Step 5 Preview: 40.0 (#57)

BenchmarkCommand AStep 5 Preview
LMArena Hard Prompts13261465
Kagi LLM Benchmark28.8%—
CritPt—20.9%
DTBench61.3%—
LMCA10.3%—

Math Step 5 Preview leads

Command A: 36.2 (#171), Step 5 Preview: 46.1 (#72)

BenchmarkCommand AStep 5 Preview
LMArena Math13001470
ProofBench—42%

Knowledge Step 5 Preview leads

Command A: 37.1 (#159), Step 5 Preview: 41.2 (#112)

BenchmarkCommand AStep 5 Preview
LMArena Expert12951470
Vectara Hallucination Rate9.3%—

Multimodal Not comparable

Command A: —, Step 5 Preview: 41.0 (#41)

BenchmarkCommand AStep 5 Preview
LMArena Vision—1267

Multilingual Step 5 Preview leads

Command A: 45.3 (#170), Step 5 Preview: 53.8 (#54)

BenchmarkCommand AStep 5 Preview
LMArena Non-English13131432
LMArena Chinese13271519
LMArena Russian13141436
LMArena Spanish13471439
LMArena French1351—
LMArena German1341—
LMArena Japanese1285—
LMArena Korean1285—

Instruction Following Step 5 Preview leads

Command A: 69.1 (#177), Step 5 Preview: 76.0 (#50)

BenchmarkCommand AStep 5 Preview
LMArena Instruction Following13091444

Long Context Step 5 Preview leads

Command A: 40.6 (#151), Step 5 Preview: 44.5 (#64)

BenchmarkCommand AStep 5 Preview
LMArena Longer Query13341455

Writing & Preference Step 5 Preview leads

Command A: 47.6 (#208), Step 5 Preview: 62.8 (#71)

BenchmarkCommand AStep 5 Preview
LMArena Text13311442
LMArena Creative Writing13191410
LMArena Multi-Turn13391447
EQ-Bench Creative Writing1145—

Frequently asked questions

Is Command A better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 36.5 on the Noometry Index.

Which is cheaper, Command A or Step 5 Preview?

Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Command A lists at $2.50 and $10.

Is Command A or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 27.2 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 256K.

How many benchmarks do Command A and Step 5 Preview share?

13 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper