# DeepSeek Coder 6.7B vs Magistral Medium

> Magistral Medium has enough public results to be ranked (#227); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-6-7b-vs-magistral-medium
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where Magistral Medium leads 39.1 to 35.8.

## Snapshot

| | DeepSeek Coder 6.7B | Magistral Medium |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 37.6 | 35.2 |
| Rank | — | 227 |
| Context | — | 262K |
| Input $/M | — | $2 |
| Output $/M | — | $5 |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 6.7B: 35.8 (#219)
- Magistral Medium: 39.1 (#161)

| Benchmark | DeepSeek Coder 6.7B | Magistral Medium |
|---|---|---|
| SciCode | — | 39.2% |
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 1319 |
| BigCodeBench Complete | 43.8% | — |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |

## Reasoning

- DeepSeek Coder 6.7B: —
- Magistral Medium: 8.6 (#348)

| Benchmark | DeepSeek Coder 6.7B | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| LMArena Hard Prompts | — | 1267 |
| Epoch Capabilities Index | 89.62 | — |
| WinoGrande | 57.6% | — |

## Math

- DeepSeek Coder 6.7B: —
- Magistral Medium: 35.1 (#189)

| Benchmark | DeepSeek Coder 6.7B | Magistral Medium |
|---|---|---|
| LMArena Math | — | 1250 |
| GSM8K | 21.3% | — |

## Knowledge

- DeepSeek Coder 6.7B: —
- Magistral Medium: 33.5 (#202)

| Benchmark | DeepSeek Coder 6.7B | Magistral Medium |
|---|---|---|
| LMArena Expert | — | 1223 |
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |

## Multilingual

- DeepSeek Coder 6.7B: —
- Magistral Medium: 39.6 (#224)

| Benchmark | DeepSeek Coder 6.7B | Magistral Medium |
|---|---|---|
| LMArena Non-English | — | 1232 |
| LMArena Chinese | — | 1227 |
| LMArena French | — | 1267 |
| LMArena German | — | 1248 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1125 |
| LMArena Russian | — | 1224 |
| LMArena Spanish | — | 1271 |

## Instruction Following

- DeepSeek Coder 6.7B: —
- Magistral Medium: 66.0 (#211)

| Benchmark | DeepSeek Coder 6.7B | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1254 |

## Long Context

- DeepSeek Coder 6.7B: —
- Magistral Medium: 39.3 (#183)

| Benchmark | DeepSeek Coder 6.7B | Magistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1295 |

## Writing & Preference

- DeepSeek Coder 6.7B: —
- Magistral Medium: 46.3 (#219)

| Benchmark | DeepSeek Coder 6.7B | Magistral Medium |
|---|---|---|
| LMArena Text | — | 1255 |
| LMArena Creative Writing | — | 1245 |
| LMArena Multi-Turn | — | 1275 |

## FAQ

### Is DeepSeek Coder 6.7B better than Magistral Medium?

Magistral Medium has enough public results to be ranked (#227); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 6.7B or Magistral Medium better for coding?

Magistral Medium scores higher on coding benchmarks: 39.1 versus 35.8 in the Noometry coding category.

### How many benchmarks do DeepSeek Coder 6.7B and Magistral Medium share?

0 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Magistral Medium has 22.