# Codellama 70b Instruct vs Granite 3.0 8b Instruct

> Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 31.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-granite-3-0-8b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Granite 3.0 8b Instruct in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Codellama 70b Instruct leads 37.0 to 29.1.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 35.4% for Granite 3.0 8b Instruct.

## Snapshot

| | Codellama 70b Instruct | Granite 3.0 8b Instruct |
|---|---|---|
| Provider | Meta | IBM |
| Noometry Index | 33.3 | 31.1 |
| Rank | 236 | 266 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- Granite 3.0 8b Instruct: 29.1 (#297)

| Benchmark | Codellama 70b Instruct | Granite 3.0 8b Instruct |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 29.3% |
| BigCodeBench Complete | 49.6% | 35.4% |
| LMArena Coding | — | 1113 |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- Granite 3.0 8b Instruct: 20.0 (#227)

| Benchmark | Codellama 70b Instruct | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1092 |

## Math

- Codellama 70b Instruct: —
- Granite 3.0 8b Instruct: 30.3 (#211)

| Benchmark | Codellama 70b Instruct | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Math | — | 1143 |

## Knowledge

- Codellama 70b Instruct: —
- Granite 3.0 8b Instruct: 29.1 (#233)

| Benchmark | Codellama 70b Instruct | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Expert | — | 1087 |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- Granite 3.0 8b Instruct: 27.4 (#271)

| Benchmark | Codellama 70b Instruct | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Non-English | 992 | 1037 |
| LMArena Chinese | — | 1063 |
| LMArena Russian | — | 1060 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- Granite 3.0 8b Instruct: 56.2 (#271)

| Benchmark | Codellama 70b Instruct | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Instruction Following | 1024 | 1088 |

## Long Context

- Codellama 70b Instruct: —
- Granite 3.0 8b Instruct: 34.0 (#247)

| Benchmark | Codellama 70b Instruct | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1122 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- Granite 3.0 8b Instruct: 31.2 (#280)

| Benchmark | Codellama 70b Instruct | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Text | 1057 | 1096 |
| LMArena Creative Writing | — | 1071 |
| LMArena Multi-Turn | — | 1063 |

## FAQ

### Is Codellama 70b Instruct better than Granite 3.0 8b Instruct?

Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 31.1 on the Noometry Index.

### Is Codellama 70b Instruct or Granite 3.0 8b Instruct better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 29.1 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Granite 3.0 8b Instruct share?

6 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Granite 3.0 8b Instruct has 14.