# Codellama 70b Instruct vs Mistral Small

> Codellama 70b Instruct and Mistral Small score almost the same on the Noometry Index (33.7 vs 33.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-mistral-small
- 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 Mistral Small in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mistral Small leads 45.5 to 24.8.

## Snapshot

| | Codellama 70b Instruct | Mistral Small |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 33.7 | 33.4 |
| Rank | 237 | 243 |
| Context | — | 262K |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Mistral Small: 34.0 (#247)

| Benchmark | Codellama 70b Instruct | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 36.1% |
| BigCodeBench Complete | 49.6% | 46.6% |
| SciCode | — | 26.5% |
| LiveBench Coding | — | 36.2% |
| LMArena Coding | — | 1362 |
| ALE-Bench | — | 497.62 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Mistral Small: 28.1 (#93)

| Benchmark | Codellama 70b Instruct | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Mistral Small: 19.8 (#250)

| Benchmark | Codellama 70b Instruct | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1335 |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |

## Math

- Codellama 70b Instruct: —
- Mistral Small: 16.4 (#293)

| Benchmark | Codellama 70b Instruct | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| LMArena Math | — | 1341 |
| MATH Level 5 | — | 46.8% |

## Knowledge

- Codellama 70b Instruct: —
- Mistral Small: 31.0 (#222)

| Benchmark | Codellama 70b Instruct | Mistral Small |
|---|---|---|
| GPQA Diamond | — | 47.5% |
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1291 |
| MMLU | — | 68.7% |

## Multimodal

- Codellama 70b Instruct: —
- Mistral Small: 33.5 (#96)

| Benchmark | Codellama 70b Instruct | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Mistral Small: 45.5 (#169)

| Benchmark | Codellama 70b Instruct | Mistral Small |
|---|---|---|
| LMArena Non-English | 992 | 1315 |
| LMArena Chinese | — | 1340 |
| LMArena French | — | 1337 |
| LMArena German | — | 1340 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1259 |
| LMArena Russian | — | 1324 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Mistral Small: 66.4 (#209)

| Benchmark | Codellama 70b Instruct | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1024 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- Codellama 70b Instruct: —
- Mistral Small: 40.4 (#156)

| Benchmark | Codellama 70b Instruct | Mistral Small |
|---|---|---|
| LMArena Longer Query | — | 1327 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Mistral Small: 52.5 (#171)

| Benchmark | Codellama 70b Instruct | Mistral Small |
|---|---|---|
| LMArena Text | 1057 | 1338 |
| LMArena Creative Writing | — | 1305 |
| LMArena Multi-Turn | — | 1344 |
| LiveBench Language | — | 30.5% |

## FAQ

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

Codellama 70b Instruct and Mistral Small score almost the same on the Noometry Index (33.7 vs 33.4), so choose on price, context window or the category you care about most.

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

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 34.0 in the Noometry coding category.

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

6 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Mistral Small has 39.