# Codellama 70b Instruct vs DeepSeek Coder 6.7B

> Codellama 70b Instruct has enough public results to be ranked (#236); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-deepseek-coder-6-7b
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and DeepSeek Coder 6.7B in 0 categories; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 43.8% for DeepSeek Coder 6.7B.

## Snapshot

| | Codellama 70b Instruct | DeepSeek Coder 6.7B |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 33.3 | 37.1 |
| Rank | 236 | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- DeepSeek Coder 6.7B: 35.2 (#216)

| Benchmark | Codellama 70b Instruct | DeepSeek Coder 6.7B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 35.5% |
| BigCodeBench Complete | 49.6% | 43.8% |
| HumanEval+ | 65.9% | 71.3% |
| MBPP+ | — | 65.6% |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- DeepSeek Coder 6.7B: —

| Benchmark | Codellama 70b Instruct | DeepSeek Coder 6.7B |
|---|---|---|
| LMArena Hard Prompts | 1052 | — |
| Epoch Capabilities Index | — | 88.88 |
| WinoGrande | — | 57.6% |

## Math

- Codellama 70b Instruct: —
- DeepSeek Coder 6.7B: —

| Benchmark | Codellama 70b Instruct | DeepSeek Coder 6.7B |
|---|---|---|
| GSM8K | — | 21.3% |

## Knowledge

- Codellama 70b Instruct: —
- DeepSeek Coder 6.7B: —

| Benchmark | Codellama 70b Instruct | DeepSeek Coder 6.7B |
|---|---|---|
| ARC (AI2) Challenge | — | 36.4% |
| MMLU | — | 36.4% |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- DeepSeek Coder 6.7B: —

| Benchmark | Codellama 70b Instruct | DeepSeek Coder 6.7B |
|---|---|---|
| LMArena Non-English | 992 | — |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- DeepSeek Coder 6.7B: —

| Benchmark | Codellama 70b Instruct | DeepSeek Coder 6.7B |
|---|---|---|
| LMArena Instruction Following | 1024 | — |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- DeepSeek Coder 6.7B: —

| Benchmark | Codellama 70b Instruct | DeepSeek Coder 6.7B |
|---|---|---|
| LMArena Text | 1057 | — |

## FAQ

### Is Codellama 70b Instruct better than DeepSeek Coder 6.7B?

Codellama 70b Instruct has enough public results to be ranked (#236); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

### Is Codellama 70b Instruct or DeepSeek Coder 6.7B better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 35.2 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and DeepSeek Coder 6.7B share?

3 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and DeepSeek Coder 6.7B has 9.