# DeepSeek-V2.5 (Sep 2024) vs Magistral Medium

> DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 35.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-magistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Magistral Medium in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V2.5 (Sep 2024) leads 25.6 to 8.6.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Magistral Medium |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 37.6 | 35.2 |
| Rank | 200 | 227 |
| Context | — | 262K |
| Input $/M | — | $2 |
| Output $/M | — | $5 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
- Magistral Medium: 39.1 (#161)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Magistral Medium |
|---|---|---|
| LMArena Coding | 1309 | 1319 |
| Aider Polyglot | 17.8% | — |
| SciCode | — | 39.2% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
- Magistral Medium: 8.6 (#348)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |

## Math

- DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
- Magistral Medium: 35.1 (#189)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Magistral Medium |
|---|---|---|
| LMArena Math | 1288 | 1250 |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
- Magistral Medium: 33.5 (#202)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Magistral Medium |
|---|---|---|
| LMArena Expert | 1266 | 1223 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
- Magistral Medium: 39.6 (#224)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1273 | 1232 |
| LMArena Chinese | 1318 | 1227 |
| LMArena French | 1289 | 1267 |
| LMArena German | 1258 | 1248 |
| LMArena Japanese | 1228 | 1175 |
| LMArena Korean | 1209 | 1125 |
| LMArena Russian | 1289 | 1224 |
| LMArena Spanish | 1248 | 1271 |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
- Magistral Medium: 66.0 (#211)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1280 | 1254 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
- Magistral Medium: 39.3 (#183)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1301 | 1295 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
- Magistral Medium: 46.3 (#219)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Magistral Medium |
|---|---|---|
| LMArena Text | 1294 | 1255 |
| LMArena Creative Writing | 1285 | 1245 |
| LMArena Multi-Turn | 1297 | 1275 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Magistral Medium?

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 35.2 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Magistral Medium better for coding?

Magistral Medium scores higher on coding benchmarks: 39.1 versus 31.7 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Magistral Medium share?

17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Magistral Medium has 22.