# Deepseek Coder v2 vs Mistral Small 3

> Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 30.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Deepseek Coder v2 scores higher in 5 categories and Mistral Small 3 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Deepseek Coder v2 leads 32.3 to 15.3.
- The biggest single-benchmark swing is BigCodeBench Complete: 59.7% for Deepseek Coder v2 and 50.4% for Mistral Small 3.

## Snapshot

| | Deepseek Coder v2 | Mistral Small 3 |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 35.3 | 30.9 |
| Rank | 217 | 268 |
| Context | — | 33K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 37.5 (#178)
- Mistral Small 3: 36.0 (#203)

| Benchmark | Deepseek Coder v2 | Mistral Small 3 |
|---|---|---|
| BigCodeBench Instruct | 48.2% | 45.3% |
| LMArena Coding | 1251 | 1246 |
| BigCodeBench Complete | 59.7% | 50.4% |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 22.6 (#175)
- Mistral Small 3: 18.2 (#269)

| Benchmark | Deepseek Coder v2 | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1233 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.06 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 32.3 (#188)
- Mistral Small 3: 15.3 (#290)

| Benchmark | Deepseek Coder v2 | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1241 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 31.7 (#209)
- Mistral Small 3: 25.0 (#258)

| Benchmark | Deepseek Coder v2 | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1181 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.4 (#235)
- Mistral Small 3: 37.5 (#231)

| Benchmark | Deepseek Coder v2 | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1182 | 1198 |
| LMArena Chinese | 1201 | 1204 |
| LMArena French | 1184 | 1202 |
| LMArena German | 1164 | 1211 |
| LMArena Japanese | 1126 | 1111 |
| LMArena Korean | 1104 | 1188 |
| LMArena Russian | 1188 | 1216 |
| LMArena Spanish | 1153 | — |

## Instruction Following

- Deepseek Coder v2: 61.9 (#237)
- Mistral Small 3: 63.9 (#224)

| Benchmark | Deepseek Coder v2 | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1214 |

## Long Context

- Deepseek Coder v2: 37.0 (#219)
- Mistral Small 3: 37.8 (#206)

| Benchmark | Deepseek Coder v2 | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1219 | 1246 |

## Writing & Preference

- Deepseek Coder v2: 38.4 (#249)
- Mistral Small 3: 32.4 (#275)

| Benchmark | Deepseek Coder v2 | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1191 | 1234 |
| LMArena Creative Writing | 1120 | 1195 |
| LMArena Multi-Turn | 1176 | 1217 |
| EQ-Bench Creative Writing | — | 707 |

## FAQ

### Is Deepseek Coder v2 better than Mistral Small 3?

Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 30.9 on the Noometry Index.

### Is Deepseek Coder v2 or Mistral Small 3 better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 37.5 versus 36.0 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Mistral Small 3 share?

18 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Mistral Small 3 has 24.