# Codellama 70b Instruct vs Nemotron 3 Super

> Nemotron 3 Super is the stronger model overall, scoring 39.6 to 33.3 on the Noometry Index.

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

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Nemotron 3 Super in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Nemotron 3 Super leads 48.6 to 24.9.

## Snapshot

| | Codellama 70b Instruct | Nemotron 3 Super |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 33.3 | 39.6 |
| Rank | 236 | 147 |
| Context | — | 262K |
| Input $/M | — | $0.08 |
| Output $/M | — | $0.45 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- Nemotron 3 Super: 38.9 (#153)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Super |
|---|---|---|
| SciCode | — | 36% |
| WeirdML | — | 38% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1403 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 213.9 |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- Nemotron 3 Super: 17.9 (#274)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1386 |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |

## Math

- Codellama 70b Instruct: —
- Nemotron 3 Super: 37.6 (#95)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Super |
|---|---|---|
| MathArena Final-Answer Competitions | — | 60.4% |
| LMArena Math | — | 1381 |

## Knowledge

- Codellama 70b Instruct: —
- Nemotron 3 Super: 38.2 (#136)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | — | 1397 |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- Nemotron 3 Super: 48.6 (#139)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 992 | 1356 |
| LMArena Chinese | — | 1430 |
| LMArena French | — | 1404 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1336 |
| LMArena Spanish | — | 1417 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- Nemotron 3 Super: 71.4 (#149)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1024 | 1347 |

## Long Context

- Codellama 70b Instruct: —
- Nemotron 3 Super: 41.5 (#134)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | — | 1362 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- Nemotron 3 Super: 56.1 (#135)

| Benchmark | Codellama 70b Instruct | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1057 | 1378 |
| LMArena Creative Writing | — | 1317 |
| LMArena Multi-Turn | — | 1369 |

## FAQ

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

Nemotron 3 Super is the stronger model overall, scoring 39.6 to 33.3 on the Noometry Index.

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

Nemotron 3 Super scores higher on coding benchmarks: 38.9 versus 37.0 in the Noometry coding category.

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

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Nemotron 3 Super has 21.