# Deepseek Coder v2 vs Llama 3.2 90B

> Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-llama-3-2-90b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Deepseek Coder v2 leads 32.3 to 10.4.

## Snapshot

| | Deepseek Coder v2 | Llama 3.2 90B |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 35.3 | 27.1 |
| Rank | 217 | 326 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 37.5 (#178)
- Llama 3.2 90B: —

| Benchmark | Deepseek Coder v2 | Llama 3.2 90B |
|---|---|---|
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Agentic & Tool Use

- Deepseek Coder v2: —
- Llama 3.2 90B: 29.7 (#73)

| Benchmark | Deepseek Coder v2 | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |

## Reasoning

- Deepseek Coder v2: 22.6 (#175)
- Llama 3.2 90B: 20.9 (#207)

| Benchmark | Deepseek Coder v2 | Llama 3.2 90B |
|---|---|---|
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1207 | — |
| Epoch Capabilities Index | — | 125.5 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 32.3 (#188)
- Llama 3.2 90B: 10.4 (#302)

| Benchmark | Deepseek Coder v2 | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 1241 | — |
| MATH Level 5 | — | 39.4% |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 31.7 (#209)
- Llama 3.2 90B: 21.7 (#269)

| Benchmark | Deepseek Coder v2 | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
| MMLU | — | 80.3% |

## Multimodal

- Deepseek Coder v2: —
- Llama 3.2 90B: 24.9 (#119)

| Benchmark | Deepseek Coder v2 | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## Multilingual

- Deepseek Coder v2: 36.4 (#235)
- Llama 3.2 90B: —

| Benchmark | Deepseek Coder v2 | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1184 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |

## Instruction Following

- Deepseek Coder v2: 61.9 (#237)
- Llama 3.2 90B: —

| Benchmark | Deepseek Coder v2 | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1180 | — |

## Long Context

- Deepseek Coder v2: 37.0 (#219)
- Llama 3.2 90B: —

| Benchmark | Deepseek Coder v2 | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1219 | — |

## Writing & Preference

- Deepseek Coder v2: 38.4 (#249)
- Llama 3.2 90B: —

| Benchmark | Deepseek Coder v2 | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1176 | — |

## FAQ

### Is Deepseek Coder v2 better than Llama 3.2 90B?

Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 27.1 on the Noometry Index.

### How many benchmarks do Deepseek Coder v2 and Llama 3.2 90B share?

0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Llama 3.2 90B has 9.