# Codellama 70b Instruct vs Nemotron 3 Ultra

> Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-nemotron-3-ultra
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Nemotron 3 Ultra in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 33.4.

## Snapshot

| | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 33.7 | 42.5 |
| Rank | 237 | 113 |
| Context | — | 262K |
| Input $/M | — | $0.50 |
| Output $/M | — | $2.20 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Nemotron 3 Ultra: 38.1 (#182)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1468 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Nemotron 3 Ultra: 23.4 (#126)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Nemotron 3 Ultra: 31.0 (#82)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1452 |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |

## Math

- Codellama 70b Instruct: —
- Nemotron 3 Ultra: 35.3 (#187)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
| LMArena Math | — | 1457 |

## Knowledge

- Codellama 70b Instruct: —
- Nemotron 3 Ultra: 52.5 (#61)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | — | 85.4% |
| LMArena Expert | — | 1472 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Nemotron 3 Ultra: 53.5 (#64)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 992 | 1427 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Russian | — | 1417 |
| LMArena Spanish | — | 1454 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Nemotron 3 Ultra: 74.7 (#88)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1024 | 1418 |

## Long Context

- Codellama 70b Instruct: —
- Nemotron 3 Ultra: 43.9 (#81)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | — | 1437 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Nemotron 3 Ultra: 66.3 (#36)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1057 | 1445 |
| LMArena Creative Writing | — | 1398 |
| EQ-Bench Creative Writing | — | 1692 |
| LMArena Multi-Turn | — | 1411 |

## FAQ

### Is Codellama 70b Instruct better than Nemotron 3 Ultra?

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or Nemotron 3 Ultra better for coding?

They score almost the same on coding (37.6 vs 38.1); test both on your own repository before choosing.

### How many benchmarks do Codellama 70b Instruct and Nemotron 3 Ultra share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Nemotron 3 Ultra has 30.