# Command R+ vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-r-plus-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Command R+ scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 9.2.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $2.50 / $10 for Command R+.
- Step 5 Preview accepts more context: 1.02M tokens versus 128K.
- Command R+ has downloadable open weights; the other is API-only.

## Snapshot

| | Command R+ | Step 5 Preview |
|---|---|---|
| Provider | Cohere | StepFun |
| Noometry Index | 32.4 | 47.9 |
| Rank | 257 | 58 |
| Context | 128K | 1.02M |
| Input $/M | $2.50 | $1 |
| Output $/M | $10 | $2.70 |
| Weights | Open | Proprietary |

## Coding

- Command R+: 29.1 (#309)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Command R+ | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1187 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |

## Reasoning

- Command R+: 9.2 (#344)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Command R+ | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1465 |
| SimpleBench | 17.4% | — |
| CritPt | — | 20.9% |
| LiveBench Reasoning | 24.8% | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| Epoch Capabilities Index | 119.34 | — |
| LiveBench | 31.8% | — |

## Math

- Command R+: 28.9 (#242)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Command R+ | Step 5 Preview |
|---|---|---|
| LMArena Math | 1188 | 1470 |
| ProofBench | — | 42% |
| LiveBench Math | 21.3% | — |

## Knowledge

- Command R+: 36.4 (#169)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Command R+ | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1174 | 1470 |
| Vectara Hallucination Rate | 6.9% | — |
| MMLU | 69.4% | — |

## Multimodal

- Command R+: —
- Step 5 Preview: 41.0 (#41)

| Benchmark | Command R+ | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |

## Multilingual

- Command R+: 38.6 (#227)
- Step 5 Preview: 53.8 (#54)

| Benchmark | Command R+ | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1216 | 1432 |
| LMArena Chinese | 1226 | 1519 |
| LMArena Russian | 1227 | 1436 |
| LMArena Spanish | 1189 | 1439 |
| LMArena French | 1209 | — |
| LMArena German | 1216 | — |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |

## Instruction Following

- Command R+: 60.0 (#254)
- Step 5 Preview: 76.0 (#50)

| Benchmark | Command R+ | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1197 | 1444 |
| LiveBench Instruction Following | 57.6% | — |

## Long Context

- Command R+: 37.3 (#219)
- Step 5 Preview: 44.5 (#64)

| Benchmark | Command R+ | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1230 | 1455 |

## Writing & Preference

- Command R+: 43.5 (#228)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Command R+ | Step 5 Preview |
|---|---|---|
| LMArena Text | 1229 | 1442 |
| LMArena Creative Writing | 1235 | 1410 |
| LMArena Multi-Turn | 1213 | 1447 |
| LiveBench Language | 29.7% | — |

## FAQ

### Is Command R+ better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 32.4 on the Noometry Index.

### Which is cheaper, Command R+ 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 R+ lists at $2.50 and $10.

### Is Command R+ or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 29.1 in the Noometry coding category.

### Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 128K.

### How many benchmarks do Command R+ and Step 5 Preview share?

13 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Step 5 Preview has 18.