# Llama 3.1 Nemotron 70b Instruct vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 37.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-1-nemotron-70b-instruct-vs-step-5-preview
- Last updated: 2026-10-12
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Llama 3.1 Nemotron 70b Instruct 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 35.9.
- Llama 3.1 Nemotron 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Llama 3.1 Nemotron 70b Instruct | Step 5 Preview |
|---|---|---|
| Provider | NVIDIA | StepFun |
| Noometry Index | 37.6 | 47.9 |
| Rank | 203 | 58 |
| Context | — | 1.02M |
| Input $/M | — | $1 |
| Output $/M | — | $2.70 |
| Weights | Open | Proprietary |

## Coding

- Llama 3.1 Nemotron 70b Instruct: 35.9 (#216)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Llama 3.1 Nemotron 70b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1272 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| BigCodeBench Instruct | 38.7% | — |
| BigCodeBench Complete | 48.2% | — |

## Reasoning

- Llama 3.1 Nemotron 70b Instruct: 25.0 (#152)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Llama 3.1 Nemotron 70b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1266 | 1465 |
| CritPt | — | 20.9% |

## Math

- Llama 3.1 Nemotron 70b Instruct: 35.5 (#182)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Llama 3.1 Nemotron 70b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Math | 1271 | 1470 |
| ProofBench | — | 42% |

## Knowledge

- Llama 3.1 Nemotron 70b Instruct: 34.1 (#199)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Llama 3.1 Nemotron 70b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1242 | 1470 |

## Multimodal

- Llama 3.1 Nemotron 70b Instruct: —
- Step 5 Preview: 41.0 (#41)

| Benchmark | Llama 3.1 Nemotron 70b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |

## Multilingual

- Llama 3.1 Nemotron 70b Instruct: 40.5 (#217)
- Step 5 Preview: 53.8 (#54)

| Benchmark | Llama 3.1 Nemotron 70b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1245 | 1432 |
| LMArena Chinese | 1263 | 1519 |
| LMArena Russian | 1227 | 1436 |
| LMArena Spanish | — | 1439 |

## Instruction Following

- Llama 3.1 Nemotron 70b Instruct: 65.9 (#213)
- Step 5 Preview: 76.0 (#50)

| Benchmark | Llama 3.1 Nemotron 70b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1252 | 1444 |

## Long Context

- Llama 3.1 Nemotron 70b Instruct: 37.6 (#215)
- Step 5 Preview: 44.5 (#64)

| Benchmark | Llama 3.1 Nemotron 70b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1238 | 1455 |

## Writing & Preference

- Llama 3.1 Nemotron 70b Instruct: 48.4 (#203)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Llama 3.1 Nemotron 70b Instruct | Step 5 Preview |
|---|---|---|
| LMArena Text | 1283 | 1442 |
| LMArena Creative Writing | 1269 | 1410 |
| LMArena Multi-Turn | 1275 | 1447 |

## FAQ

### Is Llama 3.1 Nemotron 70b Instruct better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 37.6 on the Noometry Index.

### Is Llama 3.1 Nemotron 70b Instruct or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 35.9 in the Noometry coding category.

### How many benchmarks do Llama 3.1 Nemotron 70b Instruct and Step 5 Preview share?

12 benchmarks have published results for both models. Llama 3.1 Nemotron 70b Instruct has 14 scored results on Noometry and Step 5 Preview has 18.