# Command A vs Step 3.7 Flash

> Command A and Step 3.7 Flash score almost the same on the Noometry Index (36.5 vs 37.3), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/command-a-vs-step-3-7-flash
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Step 3.7 Flash leads 40.0 to 27.2.
- Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $2.50 / $10 for Command A.

## Snapshot

| | Command A | Step 3.7 Flash |
|---|---|---|
| Provider | Cohere | StepFun |
| Noometry Index | 36.5 | 37.3 |
| Rank | 215 | 207 |
| Context | 256K | 256K |
| Input $/M | $2.50 | $0.18 |
| Output $/M | $10 | $1.11 |
| Weights | Open | Open |

## Coding

- Command A: 27.2 (#322)
- Step 3.7 Flash: 40.0 (#150)

| Benchmark | Command A | Step 3.7 Flash |
|---|---|---|
| Aider Polyglot | 12% | — |
| SciCode | — | 40% |
| LMArena Coding | 1330 | — |
| ALE-Bench | — | 694.12 |

## Agentic & Tool Use

- Command A: 35.9 (#40)
- Step 3.7 Flash: —

| Benchmark | Command A | Step 3.7 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |

## Reasoning

- Command A: 18.3 (#283)
- Step 3.7 Flash: 21.6 (#219)

| Benchmark | Command A | Step 3.7 Flash |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | — |
| NYT Connections (extended) | — | 39.7% |
| CritPt | — | 2.3% |
| LMArena Hard Prompts | 1326 | — |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |

## Math

- Command A: 36.2 (#171)
- Step 3.7 Flash: 42.9 (#82)

| Benchmark | Command A | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| LMArena Math | 1300 | — |

## Knowledge

- Command A: 37.1 (#159)
- Step 3.7 Flash: —

| Benchmark | Command A | Step 3.7 Flash |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1295 | — |

## Multilingual

- Command A: 45.3 (#170)
- Step 3.7 Flash: —

| Benchmark | Command A | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1313 | — |
| LMArena Chinese | 1327 | — |
| LMArena French | 1351 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1285 | — |
| LMArena Korean | 1285 | — |
| LMArena Russian | 1314 | — |
| LMArena Spanish | 1347 | — |

## Instruction Following

- Command A: 69.1 (#177)
- Step 3.7 Flash: —

| Benchmark | Command A | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1309 | — |

## Long Context

- Command A: 40.6 (#151)
- Step 3.7 Flash: —

| Benchmark | Command A | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1334 | — |

## Writing & Preference

- Command A: 47.6 (#208)
- Step 3.7 Flash: —

| Benchmark | Command A | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1331 | — |
| LMArena Creative Writing | 1319 | — |
| EQ-Bench Creative Writing | 1145 | — |
| LMArena Multi-Turn | 1339 | — |

## FAQ

### Is Command A better than Step 3.7 Flash?

Command A and Step 3.7 Flash score almost the same on the Noometry Index (36.5 vs 37.3), so choose on price, context window or the category you care about most.

### Which is cheaper, Command A or Step 3.7 Flash?

Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; Command A lists at $2.50 and $10.

### Is Command A or Step 3.7 Flash better for coding?

Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 27.2 in the Noometry coding category.

### Which has the bigger context window?

Both accept 256K tokens.

### How many benchmarks do Command A and Step 3.7 Flash share?

0 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Step 3.7 Flash has 5.