# Deepseek Coder v2 vs Mistral Medium

> Deepseek Coder v2 and Mistral Medium score almost the same on the Noometry Index (35.9 vs 36.3), so choose on price, context window or the category you care about most.

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

## Summary

- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 3 categories and Mistral Medium in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 38.2.

## Snapshot

| | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 35.9 | 36.3 |
| Rank | 220 | 218 |
| Context | — | 262K |
| Input $/M | — | $1.50 |
| Output $/M | — | $7.50 |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 38.1 (#183)
- Mistral Medium: 34.2 (#243)

| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Coding | 1251 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 763.98 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Agentic & Tool Use

- Deepseek Coder v2: —
- Mistral Medium: 28.3 (#90)

| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |

## Reasoning

- Deepseek Coder v2: 23.6 (#176)
- Mistral Medium: 24.0 (#167)

| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1426 |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| DTBench | — | 75.5% |
| LMCA | — | 26.1% |
| Surface Evolver Bench | — | 26.9% |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 34.9 (#190)
- Mistral Medium: 28.1 (#245)

| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Math | 1241 | 1408 |
| OTIS Mock AIME 2024-2025 | — | 32.2% |
| ProofBench | — | 9% |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 32.3 (#212)
- Mistral Medium: 25.0 (#265)

| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Expert | 1181 | 1408 |
| GPQA Diamond | — | 59.5% |
| Humanity's Last Exam | — | 4.5% |
| Vectara Hallucination Rate | — | 22.7% |
| ARC (AI2) Challenge | 64.3% | — |

## Multimodal

- Deepseek Coder v2: —
- Mistral Medium: 35.3 (#88)

| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Vision | — | 1172 |

## Multilingual

- Deepseek Coder v2: 36.3 (#240)
- Mistral Medium: 52.1 (#91)

| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1182 | 1408 |
| LMArena Chinese | 1201 | 1447 |
| LMArena French | 1185 | 1459 |
| LMArena German | 1164 | 1432 |
| LMArena Japanese | 1126 | 1378 |
| LMArena Korean | 1104 | 1380 |
| LMArena Russian | 1188 | 1411 |
| LMArena Spanish | 1153 | 1433 |

## Instruction Following

- Deepseek Coder v2: 61.7 (#242)
- Mistral Medium: 73.7 (#116)

| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1180 | 1398 |

## Long Context

- Deepseek Coder v2: 37.0 (#224)
- Mistral Medium: 42.9 (#114)

| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1219 | 1406 |

## Writing & Preference

- Deepseek Coder v2: 38.2 (#253)
- Mistral Medium: 60.0 (#103)

| Benchmark | Deepseek Coder v2 | Mistral Medium |
|---|---|---|
| LMArena Text | 1191 | 1424 |
| LMArena Creative Writing | 1120 | 1391 |
| LMArena Multi-Turn | 1177 | 1418 |
| Short-Story Creative Writing | — | 77.3% |

## FAQ

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

Deepseek Coder v2 and Mistral Medium score almost the same on the Noometry Index (35.9 vs 36.3), so choose on price, context window or the category you care about most.

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

Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 34.2 in the Noometry coding category.

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

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Mistral Medium has 36.