# Llama 3.1 Nemotron Ultra 253b v1 vs Llama2 70b Steerlm Chat

> Llama 3.1 Nemotron Ultra 253b v1 is the stronger model overall, scoring 36.7 to 31.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-3-1-nemotron-ultra-253b-v1-vs-llama2-70b-steerlm-chat
- Last updated: 2026-10-10
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. Llama 3.1 Nemotron Ultra 253b v1 scores higher in 7 categories and Llama2 70b Steerlm Chat in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3.1 Nemotron Ultra 253b v1 leads 52.2 to 31.6.

## Snapshot

| | Llama 3.1 Nemotron Ultra 253b v1 | Llama2 70b Steerlm Chat |
|---|---|---|
| Provider | NVIDIA | NVIDIA |
| Noometry Index | 36.7 | 31.8 |
| Rank | 213 | 268 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177)
- Llama2 70b Steerlm Chat: 29.9 (#300)

| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1312 | 1025 |

## Agentic & Tool Use

- Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149)
- Llama2 70b Steerlm Chat: —

| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama2 70b Steerlm Chat |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10% | — |

## Reasoning

- Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134)
- Llama2 70b Steerlm Chat: 20.0 (#246)

| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1316 | 1047 |

## Math

- Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152)
- Llama2 70b Steerlm Chat: 31.3 (#226)

| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1360 | 1072 |

## Multilingual

- Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187)
- Llama2 70b Steerlm Chat: 28.8 (#270)

| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1282 | 1063 |
| LMArena Russian | 1284 | — |

## Instruction Following

- Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178)
- Llama2 70b Steerlm Chat: 54.2 (#279)

| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1308 | 1060 |

## Long Context

- Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177)
- Llama2 70b Steerlm Chat: 30.4 (#288)

| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1299 | 998 |

## Writing & Preference

- Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175)
- Llama2 70b Steerlm Chat: 31.6 (#283)

| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1320 | 1098 |
| LMArena Creative Writing | 1314 | 1091 |
| LMArena Multi-Turn | 1317 | 1058 |

## FAQ

### Is Llama 3.1 Nemotron Ultra 253b v1 better than Llama2 70b Steerlm Chat?

Llama 3.1 Nemotron Ultra 253b v1 is the stronger model overall, scoring 36.7 to 31.8 on the Noometry Index.

### Is Llama 3.1 Nemotron Ultra 253b v1 or Llama2 70b Steerlm Chat better for coding?

Llama 3.1 Nemotron Ultra 253b v1 scores higher on coding benchmarks: 38.4 versus 29.9 in the Noometry coding category.

### How many benchmarks do Llama 3.1 Nemotron Ultra 253b v1 and Llama2 70b Steerlm Chat share?

9 benchmarks have published results for both models. Llama 3.1 Nemotron Ultra 253b v1 has 11 scored results on Noometry and Llama2 70b Steerlm Chat has 9.