# Llama 4 Scout vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 27.7 on the Noometry Index. Llama 4 Scout costs 9.5× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/llama-4-scout-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and Step 5 Preview in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 5 Preview leads 51.8 to 20.2.
- The biggest single-benchmark swing is SciCode: 17% for Llama 4 Scout and 58.9% for Step 5 Preview.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.

## Snapshot

| | Llama 4 Scout | Step 5 Preview |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 27.7 | 47.9 |
| Rank | 330 | 58 |
| Context | 128K | 1.02M |
| Input $/M | $0.10 | $1 |
| Output $/M | $0.30 | $2.70 |
| Weights | Open | Proprietary |

## Coding

- Llama 4 Scout: 20.2 (#339)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Llama 4 Scout | Step 5 Preview |
|---|---|---|
| SciCode | 17% | 58.9% |
| LMArena Coding | 1286 | 1480 |
| SWE-bench Verified (bash only) | 9.1% | — |
| LMArena WebDev | — | 1564 |
| BigCodeBench Complete | 43.1% | — |

## Agentic & Tool Use

- Llama 4 Scout: 24.6 (#119)
- Step 5 Preview: —

| Benchmark | Llama 4 Scout | Step 5 Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |

## Reasoning

- Llama 4 Scout: 9.1 (#345)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Llama 4 Scout | Step 5 Preview |
|---|---|---|
| CritPt | 0% | 20.9% |
| LMArena Hard Prompts | 1266 | 1465 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |

## Math

- Llama 4 Scout: 19.6 (#286)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Llama 4 Scout | Step 5 Preview |
|---|---|---|
| LMArena Math | 1287 | 1470 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| ProofBench | — | 42% |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |

## Knowledge

- Llama 4 Scout: 31.9 (#217)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Llama 4 Scout | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1235 | 1470 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |

## Multimodal

- Llama 4 Scout: 32.2 (#102)
- Step 5 Preview: 41.0 (#41)

| Benchmark | Llama 4 Scout | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1118 | 1267 |
| SpatialViz-Bench | 34.2% | — |

## Multilingual

- Llama 4 Scout: 41.0 (#212)
- Step 5 Preview: 53.8 (#54)

| Benchmark | Llama 4 Scout | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1252 | 1432 |
| LMArena Chinese | 1255 | 1519 |
| LMArena Russian | 1263 | 1436 |
| LMArena Spanish | 1278 | 1439 |
| LMArena French | 1282 | — |
| LMArena German | 1272 | — |
| LMArena Japanese | 1206 | — |
| LMArena Korean | 1207 | — |

## Instruction Following

- Llama 4 Scout: 65.8 (#217)
- Step 5 Preview: 76.0 (#50)

| Benchmark | Llama 4 Scout | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1248 | 1444 |
| IFEval | 81.8% | — |

## Long Context

- Llama 4 Scout: 27.5 (#294)
- Step 5 Preview: 44.5 (#64)

| Benchmark | Llama 4 Scout | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1265 | 1455 |
| Fiction.LiveBench | 36% | — |

## Writing & Preference

- Llama 4 Scout: 37.0 (#261)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Llama 4 Scout | Step 5 Preview |
|---|---|---|
| LMArena Text | 1279 | 1442 |
| LMArena Creative Writing | 1249 | 1410 |
| LMArena Multi-Turn | 1280 | 1447 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |

## FAQ

### Is Llama 4 Scout better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 27.7 on the Noometry Index. Llama 4 Scout costs 9.5× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

### Which is cheaper, Llama 4 Scout or Step 5 Preview?

Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Step 5 Preview lists at $1 and $2.70.

### Is Llama 4 Scout or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 20.2 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 Llama 4 Scout and Step 5 Preview share?

16 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Step 5 Preview has 18.