# Llama 13b vs Nemotron 3 Ultra

> Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 24.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama-13b-vs-nemotron-3-ultra
- Last updated: 2026-10-10
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Nemotron 3 Ultra in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 13.8.

## Snapshot

| | Llama 13b | Nemotron 3 Ultra |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 24.4 | 42.5 |
| Rank | 348 | 113 |
| Context | — | 262K |
| Input $/M | — | $0.50 |
| Output $/M | — | $2.20 |
| Weights | Open | Open |

## Coding

- Llama 13b: 21.4 (#337)
- Nemotron 3 Ultra: 38.1 (#182)

| Benchmark | Llama 13b | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 683 | 1468 |
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |

## Agentic & Tool Use

- Llama 13b: —
- Nemotron 3 Ultra: 23.4 (#126)

| Benchmark | Llama 13b | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |

## Reasoning

- Llama 13b: 14.0 (#329)
- Nemotron 3 Ultra: 31.0 (#82)

| Benchmark | Llama 13b | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 728 | 1452 |
| Epoch Capabilities Index | 100.58 | 146.17 |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| BIG-Bench Hard | 37.9% | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |

## Math

- Llama 13b: 26.7 (#256)
- Nemotron 3 Ultra: 35.3 (#187)

| Benchmark | Llama 13b | Nemotron 3 Ultra |
|---|---|---|
| LMArena Math | 838 | 1457 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
| GSM8K | 20.6% | — |

## Knowledge

- Llama 13b: —
- Nemotron 3 Ultra: 52.5 (#61)

| Benchmark | Llama 13b | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | — | 85.4% |
| LMArena Expert | — | 1472 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |

## Multimodal

- Llama 13b: —
- Nemotron 3 Ultra: —

| Benchmark | Llama 13b | Nemotron 3 Ultra |
|---|---|---|
| ScienceQA | 43.3% | — |

## Multilingual

- Llama 13b: 16.6 (#297)
- Nemotron 3 Ultra: 53.5 (#64)

| Benchmark | Llama 13b | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 819 | 1427 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Russian | — | 1417 |
| LMArena Spanish | — | 1454 |

## Instruction Following

- Llama 13b: 36.7 (#305)
- Nemotron 3 Ultra: 74.7 (#88)

| Benchmark | Llama 13b | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 781 | 1418 |

## Long Context

- Llama 13b: —
- Nemotron 3 Ultra: 43.9 (#81)

| Benchmark | Llama 13b | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | — | 1437 |

## Writing & Preference

- Llama 13b: 13.8 (#312)
- Nemotron 3 Ultra: 66.3 (#36)

| Benchmark | Llama 13b | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 834 | 1445 |
| LMArena Creative Writing | 794 | 1398 |
| LMArena Multi-Turn | 753 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |

## FAQ

### Is Llama 13b better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 24.4 on the Noometry Index.

### Is Llama 13b or Nemotron 3 Ultra better for coding?

Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 21.4 in the Noometry coding category.

### How many benchmarks do Llama 13b and Nemotron 3 Ultra share?

9 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Nemotron 3 Ultra has 30.