# DeepSeek-V3.1 vs Mistral Medium 3.5

> DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 40.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-mistral-medium-3-5
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 4 categories and Mistral Medium 3.5 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1 leads 27.9 to 17.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 53.2% for DeepSeek-V3.1 and 41.4% for Mistral Medium 3.5.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 164K.

## Snapshot

| | DeepSeek-V3.1 | Mistral Medium 3.5 |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 42.8 | 40.2 |
| Rank | 108 | 152 |
| Context | 164K | 262K |
| Input $/M | $0.25 | $1.50 |
| Output $/M | $0.95 | $7.50 |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1: 40.3 (#144)
- Mistral Medium 3.5: 36.0 (#213)

| Benchmark | DeepSeek-V3.1 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1417 | 1461 |
| LMArena WebDev | — | 1264 |
| WeirdML | 38.4% | — |

## Reasoning

- DeepSeek-V3.1: 27.9 (#110)
- Mistral Medium 3.5: 17.3 (#295)

| Benchmark | DeepSeek-V3.1 | Mistral Medium 3.5 |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 41.4% |
| LMArena Hard Prompts | 1417 | 1436 |
| Epoch Capabilities Index | 139.92 | 141.35 |
| SimpleBench | 40% | — |
| NYT Connections (extended) | — | 12.9% |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| ForecastBench | 58 | — |

## Math

- DeepSeek-V3.1: 38.9 (#122)
- Mistral Medium 3.5: 39.1 (#113)

| Benchmark | DeepSeek-V3.1 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1420 | 1431 |

## Knowledge

- DeepSeek-V3.1: 43.7 (#90)
- Mistral Medium 3.5: 40.0 (#126)

| Benchmark | DeepSeek-V3.1 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1405 | 1432 |
| Vectara Hallucination Rate | 5.5% | — |

## Multimodal

- DeepSeek-V3.1: —
- Mistral Medium 3.5: 38.3 (#65)

| Benchmark | DeepSeek-V3.1 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1223 |

## Multilingual

- DeepSeek-V3.1: 51.6 (#106)
- Mistral Medium 3.5: 51.9 (#100)

| Benchmark | DeepSeek-V3.1 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1400 | 1404 |
| LMArena Chinese | 1469 | 1442 |
| LMArena French | 1447 | 1448 |
| LMArena German | 1411 | 1451 |
| LMArena Korean | 1337 | 1385 |
| LMArena Russian | 1405 | 1395 |
| LMArena Spanish | 1431 | 1409 |
| LMArena Japanese | 1378 | — |

## Instruction Following

- DeepSeek-V3.1: 73.9 (#110)
- Mistral Medium 3.5: 74.6 (#90)

| Benchmark | DeepSeek-V3.1 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1400 | 1415 |

## Long Context

- DeepSeek-V3.1: 36.3 (#232)
- Mistral Medium 3.5: 43.2 (#103)

| Benchmark | DeepSeek-V3.1 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1422 | 1415 |
| Fiction.LiveBench | 52.8% | — |

## Writing & Preference

- DeepSeek-V3.1: 60.3 (#98)
- Mistral Medium 3.5: 58.5 (#117)

| Benchmark | DeepSeek-V3.1 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1420 | 1421 |
| LMArena Creative Writing | 1401 | 1374 |
| LMArena Multi-Turn | 1408 | 1423 |
| EQ-Bench Creative Writing | 1436 | — |
| EQ-Bench 4 | — | 993 |

## FAQ

### Is DeepSeek-V3.1 better than Mistral Medium 3.5?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 40.2 on the Noometry Index.

### Which is cheaper, DeepSeek-V3.1 or Mistral Medium 3.5?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is DeepSeek-V3.1 or Mistral Medium 3.5 better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 36.0 in the Noometry coding category.

### Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 164K.

### How many benchmarks do DeepSeek-V3.1 and Mistral Medium 3.5 share?

18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Mistral Medium 3.5 has 22.