# Deepseek Coder v2 vs Magistral Medium

> Deepseek Coder v2 and Magistral Medium score almost the same on the Noometry Index (35.9 vs 35.2), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-magistral-medium
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Magistral Medium in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Deepseek Coder v2 leads 23.6 to 8.6.

## Snapshot

| | Deepseek Coder v2 | Magistral Medium |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 35.9 | 35.2 |
| Rank | 220 | 227 |
| Context | — | 262K |
| Input $/M | — | $2 |
| Output $/M | — | $5 |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 38.1 (#183)
- Magistral Medium: 39.1 (#161)

| Benchmark | Deepseek Coder v2 | Magistral Medium |
|---|---|---|
| LMArena Coding | 1251 | 1319 |
| SciCode | — | 39.2% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 23.6 (#176)
- Magistral Medium: 8.6 (#348)

| Benchmark | Deepseek Coder v2 | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 34.9 (#190)
- Magistral Medium: 35.1 (#189)

| Benchmark | Deepseek Coder v2 | Magistral Medium |
|---|---|---|
| LMArena Math | 1241 | 1250 |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 32.3 (#212)
- Magistral Medium: 33.5 (#202)

| Benchmark | Deepseek Coder v2 | Magistral Medium |
|---|---|---|
| LMArena Expert | 1181 | 1223 |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.3 (#240)
- Magistral Medium: 39.6 (#224)

| Benchmark | Deepseek Coder v2 | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1182 | 1232 |
| LMArena Chinese | 1201 | 1227 |
| LMArena French | 1185 | 1267 |
| LMArena German | 1164 | 1248 |
| LMArena Japanese | 1126 | 1175 |
| LMArena Korean | 1104 | 1125 |
| LMArena Russian | 1188 | 1224 |
| LMArena Spanish | 1153 | 1271 |

## Instruction Following

- Deepseek Coder v2: 61.7 (#242)
- Magistral Medium: 66.0 (#211)

| Benchmark | Deepseek Coder v2 | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1180 | 1254 |

## Long Context

- Deepseek Coder v2: 37.0 (#224)
- Magistral Medium: 39.3 (#183)

| Benchmark | Deepseek Coder v2 | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1219 | 1295 |

## Writing & Preference

- Deepseek Coder v2: 38.2 (#253)
- Magistral Medium: 46.3 (#219)

| Benchmark | Deepseek Coder v2 | Magistral Medium |
|---|---|---|
| LMArena Text | 1191 | 1255 |
| LMArena Creative Writing | 1120 | 1245 |
| LMArena Multi-Turn | 1177 | 1275 |

## FAQ

### Is Deepseek Coder v2 better than Magistral Medium?

Deepseek Coder v2 and Magistral Medium score almost the same on the Noometry Index (35.9 vs 35.2), so choose on price, context window or the category you care about most.

### Is Deepseek Coder v2 or Magistral Medium better for coding?

Magistral Medium scores higher on coding benchmarks: 39.1 versus 38.1 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Magistral Medium share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Magistral Medium has 22.