# C4ai Aya Expanse 32b vs Codellama 70b Instruct

> C4ai Aya Expanse 32b is the stronger model overall, scoring 35.3 to 33.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/c4ai-aya-expanse-32b-vs-codellama-70b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 4 categories and Codellama 70b Instruct in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where C4ai Aya Expanse 32b leads 38.5 to 24.9.

## Snapshot

| | C4ai Aya Expanse 32b | Codellama 70b Instruct |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 35.3 | 33.3 |
| Rank | 216 | 236 |
| Context | 128K | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- C4ai Aya Expanse 32b: 34.3 (#227)
- Codellama 70b Instruct: 37.0 (#189)

| Benchmark | C4ai Aya Expanse 32b | Codellama 70b Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 40.7% |
| LMArena Coding | 1197 | — |
| BigCodeBench Complete | — | 49.6% |
| HumanEval+ | — | 65.9% |

## Reasoning

- C4ai Aya Expanse 32b: 22.3 (#183)
- Codellama 70b Instruct: 19.2 (#241)

| Benchmark | C4ai Aya Expanse 32b | Codellama 70b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1052 |

## Math

- C4ai Aya Expanse 32b: 31.4 (#195)
- Codellama 70b Instruct: —

| Benchmark | C4ai Aya Expanse 32b | Codellama 70b Instruct |
|---|---|---|
| LMArena Math | 1200 | — |

## Knowledge

- C4ai Aya Expanse 32b: 32.6 (#202)
- Codellama 70b Instruct: —

| Benchmark | C4ai Aya Expanse 32b | Codellama 70b Instruct |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |

## Multilingual

- C4ai Aya Expanse 32b: 38.5 (#225)
- Codellama 70b Instruct: 24.9 (#283)

| Benchmark | C4ai Aya Expanse 32b | Codellama 70b Instruct |
|---|---|---|
| LMArena Non-English | 1213 | 992 |
| LMArena Chinese | 1210 | — |
| LMArena French | 1247 | — |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
| LMArena Korean | 1158 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1193 | — |

## Instruction Following

- C4ai Aya Expanse 32b: 62.9 (#232)
- Codellama 70b Instruct: 52.1 (#288)

| Benchmark | C4ai Aya Expanse 32b | Codellama 70b Instruct |
|---|---|---|
| LMArena Instruction Following | 1196 | 1024 |

## Long Context

- C4ai Aya Expanse 32b: 37.2 (#215)
- Codellama 70b Instruct: —

| Benchmark | C4ai Aya Expanse 32b | Codellama 70b Instruct |
|---|---|---|
| LMArena Longer Query | 1228 | — |

## Writing & Preference

- C4ai Aya Expanse 32b: 42.4 (#230)
- Codellama 70b Instruct: 33.6 (#272)

| Benchmark | C4ai Aya Expanse 32b | Codellama 70b Instruct |
|---|---|---|
| LMArena Text | 1224 | 1057 |
| LMArena Creative Writing | 1200 | — |
| LMArena Multi-Turn | 1190 | — |

## FAQ

### Is C4ai Aya Expanse 32b better than Codellama 70b Instruct?

C4ai Aya Expanse 32b is the stronger model overall, scoring 35.3 to 33.3 on the Noometry Index.

### Is C4ai Aya Expanse 32b or Codellama 70b Instruct better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 34.3 in the Noometry coding category.

### How many benchmarks do C4ai Aya Expanse 32b and Codellama 70b Instruct share?

4 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Codellama 70b Instruct has 7.