# Codellama 70b Instruct vs DeepSeek-V3

> DeepSeek-V3 is the stronger model overall, scoring 39.2 to 33.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-deepseek-v3
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and DeepSeek-V3 in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3 leads 57.6 to 33.6.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 62.2% for DeepSeek-V3.

## Snapshot

| | Codellama 70b Instruct | DeepSeek-V3 |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 33.3 | 39.2 |
| Rank | 236 | 157 |
| Context | — | 164K |
| Input $/M | — | $0.24 |
| Output $/M | — | $0.90 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- DeepSeek-V3: 41.9 (#99)

| Benchmark | Codellama 70b Instruct | DeepSeek-V3 |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 50% |
| BigCodeBench Complete | 49.6% | 62.2% |
| HumanEval+ | 65.9% | 86.6% |
| Aider Polyglot | — | 55.1% |
| SciCode | — | 35.8% |
| WeirdML | — | 36.1% |
| LiveBench Coding | — | 70.9% |
| LMArena Coding | — | 1368 |
| MBPP+ | — | 73% |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- DeepSeek-V3: —

| Benchmark | Codellama 70b Instruct | DeepSeek-V3 |
|---|---|---|
| METR Time Horizons | — | 49.6% |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- DeepSeek-V3: 20.0 (#226)

| Benchmark | Codellama 70b Instruct | DeepSeek-V3 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1365 |
| SimpleBench | — | 27.2% |
| Kagi LLM Benchmark | — | 52.3% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 65.8% |
| DTBench | — | 64.8% |
| LiveBench Data Analysis | — | 60.9% |
| LMCA | — | 15.5% |
| BIG-Bench Hard | — | 87.5% |
| Epoch Capabilities Index | — | 135.95 |
| ForecastBench | — | 59.1 |
| HellaSwag | — | 88.9% |
| LiveBench | — | 66.9% |
| PIQA | — | 84.7% |
| WinoGrande | — | 85.2% |

## Math

- Codellama 70b Instruct: —
- DeepSeek-V3: 30.4 (#208)

| Benchmark | Codellama 70b Instruct | DeepSeek-V3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 37.8% |
| Omni-MATH | — | 40.3% |
| LiveBench Math | — | 73.5% |
| LMArena Math | — | 1373 |
| MATH Level 5 | — | 75.5% |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- Codellama 70b Instruct: —
- DeepSeek-V3: 37.5 (#147)

| Benchmark | Codellama 70b Instruct | DeepSeek-V3 |
|---|---|---|
| GPQA Diamond | — | 67.6% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 26.1% |
| Vectara Hallucination Rate | — | 6.1% |
| GPQA (HELM) | — | 53.8% |
| LMArena Expert | — | 1352 |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 87.2% |
| TriviaQA | — | 82.9% |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- DeepSeek-V3: 48.8 (#138)

| Benchmark | Codellama 70b Instruct | DeepSeek-V3 |
|---|---|---|
| LMArena Non-English | 992 | 1358 |
| LMArena Chinese | — | 1390 |
| LMArena French | — | 1386 |
| LMArena German | — | 1374 |
| LMArena Japanese | — | 1333 |
| LMArena Korean | — | 1321 |
| LMArena Russian | — | 1372 |
| LMArena Spanish | — | 1358 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- DeepSeek-V3: 73.0 (#125)

| Benchmark | Codellama 70b Instruct | DeepSeek-V3 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1345 |
| LiveBench Instruction Following | — | 81.5% |
| IFEval | — | 83.2% |

## Long Context

- Codellama 70b Instruct: —
- DeepSeek-V3: 34.0 (#248)

| Benchmark | Codellama 70b Instruct | DeepSeek-V3 |
|---|---|---|
| Fiction.LiveBench | — | 50% |
| LMArena Longer Query | — | 1353 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- DeepSeek-V3: 57.6 (#124)

| Benchmark | Codellama 70b Instruct | DeepSeek-V3 |
|---|---|---|
| LMArena Text | 1057 | 1375 |
| LMArena Creative Writing | — | 1364 |
| Short-Story Creative Writing | — | 77% |
| EQ-Bench Creative Writing | — | 1472 |
| WildBench | — | 83% |
| LMArena Multi-Turn | — | 1389 |
| LiveBench Language | — | 49.1% |

## FAQ

### Is Codellama 70b Instruct better than DeepSeek-V3?

DeepSeek-V3 is the stronger model overall, scoring 39.2 to 33.3 on the Noometry Index.

### Is Codellama 70b Instruct or DeepSeek-V3 better for coding?

DeepSeek-V3 scores higher on coding benchmarks: 41.9 versus 37.0 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and DeepSeek-V3 share?

7 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and DeepSeek-V3 has 60.