# Codellama 70b Instruct vs Granite 3.1 8b Instruct

> Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-granite-3-1-8b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Granite 3.1 8b Instruct in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 3.1 8b Instruct leads 58.6 to 51.9.

## Snapshot

| | Codellama 70b Instruct | Granite 3.1 8b Instruct |
|---|---|---|
| Provider | Meta | IBM |
| Noometry Index | 33.7 | 32.4 |
| Rank | 237 | 258 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Granite 3.1 8b Instruct: 34.5 (#233)

| Benchmark | Codellama 70b Instruct | Granite 3.1 8b Instruct |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1186 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Granite 3.1 8b Instruct: 24.1 (#120)

| Benchmark | Codellama 70b Instruct | Granite 3.1 8b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.1% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Granite 3.1 8b Instruct: 22.1 (#207)

| Benchmark | Codellama 70b Instruct | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1145 |

## Math

- Codellama 70b Instruct: —
- Granite 3.1 8b Instruct: 33.0 (#209)

| Benchmark | Codellama 70b Instruct | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Math | — | 1152 |

## Knowledge

- Codellama 70b Instruct: —
- Granite 3.1 8b Instruct: 31.1 (#220)

| Benchmark | Codellama 70b Instruct | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Expert | — | 1142 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Granite 3.1 8b Instruct: 30.9 (#260)

| Benchmark | Codellama 70b Instruct | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Non-English | 992 | 1099 |
| LMArena Chinese | — | 1145 |
| LMArena Russian | — | 1092 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Granite 3.1 8b Instruct: 58.6 (#259)

| Benchmark | Codellama 70b Instruct | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Instruction Following | 1024 | 1131 |

## Long Context

- Codellama 70b Instruct: —
- Granite 3.1 8b Instruct: 35.2 (#241)

| Benchmark | Codellama 70b Instruct | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1162 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Granite 3.1 8b Instruct: 35.5 (#266)

| Benchmark | Codellama 70b Instruct | Granite 3.1 8b Instruct |
|---|---|---|
| LMArena Text | 1057 | 1150 |
| LMArena Creative Writing | — | 1129 |
| LMArena Multi-Turn | — | 1108 |

## FAQ

### Is Codellama 70b Instruct better than Granite 3.1 8b Instruct?

Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 32.4 on the Noometry Index.

### Is Codellama 70b Instruct or Granite 3.1 8b Instruct better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 34.5 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Granite 3.1 8b Instruct share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Granite 3.1 8b Instruct has 13.