# Codellama 70b Instruct vs Granite 4.1 8b

> Granite 4.1 8b is the stronger model overall, scoring 36.8 to 33.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-granite-4-1-8b
- 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 Granite 4.1 8b in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Granite 4.1 8b leads 41.8 to 24.9.

## Snapshot

| | Codellama 70b Instruct | Granite 4.1 8b |
|---|---|---|
| Provider | Meta | IBM |
| Noometry Index | 33.3 | 36.8 |
| Rank | 236 | 202 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- Granite 4.1 8b: 29.9 (#291)

| Benchmark | Codellama 70b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena WebDev | — | 1190 |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1313 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- Granite 4.1 8b: 24.6 (#142)

| Benchmark | Codellama 70b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1294 |

## Math

- Codellama 70b Instruct: —
- Granite 4.1 8b: 33.8 (#167)

| Benchmark | Codellama 70b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Math | — | 1311 |

## Knowledge

- Codellama 70b Instruct: —
- Granite 4.1 8b: 35.5 (#171)

| Benchmark | Codellama 70b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Expert | — | 1310 |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- Granite 4.1 8b: 41.8 (#199)

| Benchmark | Codellama 70b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Non-English | 992 | 1261 |
| LMArena Chinese | — | 1335 |
| LMArena Russian | — | 1238 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- Granite 4.1 8b: 67.0 (#198)

| Benchmark | Codellama 70b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Instruction Following | 1024 | 1268 |

## Long Context

- Codellama 70b Instruct: —
- Granite 4.1 8b: 38.7 (#188)

| Benchmark | Codellama 70b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Longer Query | — | 1275 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- Granite 4.1 8b: 48.3 (#199)

| Benchmark | Codellama 70b Instruct | Granite 4.1 8b |
|---|---|---|
| LMArena Text | 1057 | 1291 |
| LMArena Creative Writing | — | 1249 |
| LMArena Multi-Turn | — | 1269 |

## FAQ

### Is Codellama 70b Instruct better than Granite 4.1 8b?

Granite 4.1 8b is the stronger model overall, scoring 36.8 to 33.3 on the Noometry Index.

### Is Codellama 70b Instruct or Granite 4.1 8b better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 29.9 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Granite 4.1 8b share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Granite 4.1 8b has 13.