# Codellama 70b Instruct vs Granite 4.2 30b

> Granite 4.2 30b is the stronger model overall, scoring 41.8 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-granite-4-2-30b
- 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 Granite 4.2 30b in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Granite 4.2 30b leads 47.3 to 24.8.

## Snapshot

| | Codellama 70b Instruct | Granite 4.2 30b |
|---|---|---|
| Provider | Meta | IBM |
| Noometry Index | 33.7 | 41.8 |
| Rank | 237 | 130 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Granite 4.2 30b: 41.0 (#126)

| Benchmark | Codellama 70b Instruct | Granite 4.2 30b |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1396 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Granite 4.2 30b: 27.8 (#112)

| Benchmark | Codellama 70b Instruct | Granite 4.2 30b |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1374 |

## Knowledge

- Codellama 70b Instruct: —
- Granite 4.2 30b: 39.1 (#138)

| Benchmark | Codellama 70b Instruct | Granite 4.2 30b |
|---|---|---|
| LMArena Expert | — | 1406 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Granite 4.2 30b: 47.3 (#151)

| Benchmark | Codellama 70b Instruct | Granite 4.2 30b |
|---|---|---|
| LMArena Non-English | 992 | 1340 |
| LMArena Chinese | — | 1414 |
| LMArena Russian | — | 1343 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Granite 4.2 30b: 71.2 (#155)

| Benchmark | Codellama 70b Instruct | Granite 4.2 30b |
|---|---|---|
| LMArena Instruction Following | 1024 | 1347 |

## Long Context

- Codellama 70b Instruct: —
- Granite 4.2 30b: 41.4 (#140)

| Benchmark | Codellama 70b Instruct | Granite 4.2 30b |
|---|---|---|
| LMArena Longer Query | — | 1359 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Granite 4.2 30b: 53.8 (#156)

| Benchmark | Codellama 70b Instruct | Granite 4.2 30b |
|---|---|---|
| LMArena Text | 1057 | 1361 |
| LMArena Creative Writing | — | 1288 |
| LMArena Multi-Turn | — | 1339 |

## FAQ

### Is Codellama 70b Instruct better than Granite 4.2 30b?

Granite 4.2 30b is the stronger model overall, scoring 41.8 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or Granite 4.2 30b better for coding?

Granite 4.2 30b scores higher on coding benchmarks: 41.0 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Granite 4.2 30b share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Granite 4.2 30b has 11.