# Llama 3.2 3B vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 28.9 on the Noometry Index. Llama 3.2 3B costs 12× 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-3-2-3b-vs-step-5-preview
- Last updated: 2026-10-11
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Llama 3.2 3B scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 24.7.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 131K.
- Llama 3.2 3B has downloadable open weights; the other is API-only.

## Snapshot

| | Llama 3.2 3B | Step 5 Preview |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 28.9 | 47.9 |
| Rank | 321 | 58 |
| Context | 131K | 1.02M |
| Input $/M | $0.05 | $1 |
| Output $/M | $0.33 | $2.70 |
| Weights | Open | Proprietary |

## Coding

- Llama 3.2 3B: 27.6 (#319)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Llama 3.2 3B | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1098 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |

## Agentic & Tool Use

- Llama 3.2 3B: 20.1 (#143)
- Step 5 Preview: —

| Benchmark | Llama 3.2 3B | Step 5 Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |

## Reasoning

- Llama 3.2 3B: 21.0 (#228)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Llama 3.2 3B | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1465 |
| CritPt | — | 20.9% |

## Math

- Llama 3.2 3B: 32.4 (#214)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Llama 3.2 3B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1126 | 1470 |
| ProofBench | — | 42% |

## Knowledge

- Llama 3.2 3B: 29.7 (#235)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Llama 3.2 3B | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1090 | 1470 |

## Multimodal

- Llama 3.2 3B: —
- Step 5 Preview: 41.0 (#41)

| Benchmark | Llama 3.2 3B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |

## Multilingual

- Llama 3.2 3B: 26.2 (#281)
- Step 5 Preview: 53.8 (#54)

| Benchmark | Llama 3.2 3B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1019 | 1432 |
| LMArena Chinese | 1017 | 1519 |
| LMArena Russian | 949 | 1436 |
| LMArena German | 1056 | — |
| LMArena Spanish | — | 1439 |

## Instruction Following

- Llama 3.2 3B: 56.0 (#275)
- Step 5 Preview: 76.0 (#50)

| Benchmark | Llama 3.2 3B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1089 | 1444 |

## Long Context

- Llama 3.2 3B: 33.4 (#261)
- Step 5 Preview: 44.5 (#64)

| Benchmark | Llama 3.2 3B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1100 | 1455 |

## Writing & Preference

- Llama 3.2 3B: 24.7 (#307)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Llama 3.2 3B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1110 | 1442 |
| LMArena Creative Writing | 1094 | 1410 |
| LMArena Multi-Turn | 1105 | 1447 |
| EQ-Bench Creative Writing | 595 | — |

## FAQ

### Is Llama 3.2 3B better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 28.9 on the Noometry Index. Llama 3.2 3B costs 12× 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 3.2 3B or Step 5 Preview?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; Step 5 Preview lists at $1 and $2.70.

### Is Llama 3.2 3B or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 27.6 in the Noometry coding category.

### Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 131K.

### How many benchmarks do Llama 3.2 3B and Step 5 Preview share?

12 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Step 5 Preview has 18.