# Codellama 70b Instruct vs Mistral Small 3

> Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 30.9 on the Noometry Index.

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

## Summary

- They share 6 benchmarks with published results for both. Codellama 70b Instruct scores higher in 3 categories and Mistral Small 3 in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mistral Small 3 leads 37.5 to 24.9.

## Snapshot

| | Codellama 70b Instruct | Mistral Small 3 |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 33.3 | 30.9 |
| Rank | 236 | 268 |
| Context | — | 33K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- Mistral Small 3: 36.0 (#203)

| Benchmark | Codellama 70b Instruct | Mistral Small 3 |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 45.3% |
| BigCodeBench Complete | 49.6% | 50.4% |
| LMArena Coding | — | 1246 |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- Mistral Small 3: 18.2 (#269)

| Benchmark | Codellama 70b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1233 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.06 |

## Math

- Codellama 70b Instruct: —
- Mistral Small 3: 15.3 (#290)

| Benchmark | Codellama 70b Instruct | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| LMArena Math | — | 1240 |

## Knowledge

- Codellama 70b Instruct: —
- Mistral Small 3: 25.0 (#258)

| Benchmark | Codellama 70b Instruct | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |
| LMArena Expert | — | 1202 |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- Mistral Small 3: 37.5 (#231)

| Benchmark | Codellama 70b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 992 | 1198 |
| LMArena Chinese | — | 1204 |
| LMArena French | — | 1202 |
| LMArena German | — | 1211 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1216 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- Mistral Small 3: 63.9 (#224)

| Benchmark | Codellama 70b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1214 |

## Long Context

- Codellama 70b Instruct: —
- Mistral Small 3: 37.8 (#206)

| Benchmark | Codellama 70b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | — | 1246 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- Mistral Small 3: 32.4 (#275)

| Benchmark | Codellama 70b Instruct | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1057 | 1234 |
| LMArena Creative Writing | — | 1195 |
| EQ-Bench Creative Writing | — | 707 |
| LMArena Multi-Turn | — | 1217 |

## FAQ

### Is Codellama 70b Instruct better than Mistral Small 3?

Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 30.9 on the Noometry Index.

### Is Codellama 70b Instruct or Mistral Small 3 better for coding?

They score almost the same on coding (37.0 vs 36.0); test both on your own repository before choosing.

### How many benchmarks do Codellama 70b Instruct and Mistral Small 3 share?

6 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Mistral Small 3 has 24.