# Codellama 70b Instruct vs DeepSeek LLM 67B

> Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-deepseek-llm-67b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 3 categories and DeepSeek LLM 67B in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Codellama 70b Instruct leads 37.0 to 31.3.

## Snapshot

| | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 33.3 | 24.8 |
| Rank | 236 | 341 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- DeepSeek LLM 67B: 31.3 (#273)

| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1096 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- DeepSeek LLM 67B: 15.9 (#300)

| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1070 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 110.54 |

## Math

- Codellama 70b Instruct: —
- DeepSeek LLM 67B: 8.1 (#318)

| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0.8% |
| LMArena Math | — | 1108 |
| MATH Level 5 | — | 6.4% |

## Knowledge

- Codellama 70b Instruct: —
- DeepSeek LLM 67B: 7.1 (#308)

| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | — | 24.6% |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- DeepSeek LLM 67B: 29.5 (#262)

| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | 992 | 1073 |
| LMArena Chinese | — | 1132 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- DeepSeek LLM 67B: 55.7 (#272)

| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1079 |

## Long Context

- Codellama 70b Instruct: —
- DeepSeek LLM 67B: 33.1 (#260)

| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | — | 1092 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- DeepSeek LLM 67B: 31.8 (#277)

| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | 1057 | 1105 |
| LMArena Creative Writing | — | 1067 |
| LMArena Multi-Turn | — | 1082 |

## FAQ

### Is Codellama 70b Instruct better than DeepSeek LLM 67B?

Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 24.8 on the Noometry Index.

### Is Codellama 70b Instruct or DeepSeek LLM 67B better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 31.3 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and DeepSeek LLM 67B share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and DeepSeek LLM 67B has 15.