# DeepSeek V4.1 Flash vs Mistral Medium 3.5

> DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 39.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-1-flash-vs-mistral-medium-3-5
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Mistral Medium 3.5 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 46.2 to 16.6.
- The biggest single-benchmark swing is NYT Connections (extended): 89.6% for DeepSeek V4.1 Flash and 12.9% for Mistral Medium 3.5.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 262K.

## Snapshot

| | DeepSeek V4.1 Flash | Mistral Medium 3.5 |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 50.3 | 39.6 |
| Rank | 40 | 151 |
| Context | 1M | 262K |
| Input $/M | $0.15 | $1.50 |
| Output $/M | $0.60 | $7.50 |
| Weights | Open | Open |

## Coding

- DeepSeek V4.1 Flash: 52.8 (#29)
- Mistral Medium 3.5: 35.7 (#208)

| Benchmark | DeepSeek V4.1 Flash | Mistral Medium 3.5 |
|---|---|---|
| LMArena WebDev | 1620 | 1263 |
| LMArena Coding | 1511 | 1461 |
| SciCode | 51.9% | — |
| ALE-Bench | 1,092 | — |

## Reasoning

- DeepSeek V4.1 Flash: 46.2 (#39)
- Mistral Medium 3.5: 16.6 (#290)

| Benchmark | DeepSeek V4.1 Flash | Mistral Medium 3.5 |
|---|---|---|
| NYT Connections (extended) | 89.6% | 12.9% |
| LMArena Hard Prompts | 1485 | 1436 |
| Epoch Capabilities Index | 155.01 | 141.42 |
| Kagi LLM Benchmark | — | 41.4% |
| CritPt | 14.3% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |

## Math

- DeepSeek V4.1 Flash: 48.4 (#52)
- Mistral Medium 3.5: 36.4 (#113)

| Benchmark | DeepSeek V4.1 Flash | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1493 | 1432 |
| ProofBench | 54% | — |

## Knowledge

- DeepSeek V4.1 Flash: 41.6 (#97)
- Mistral Medium 3.5: 39.3 (#123)

| Benchmark | DeepSeek V4.1 Flash | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1505 | 1431 |

## Multimodal

- DeepSeek V4.1 Flash: —
- Mistral Medium 3.5: 37.6 (#64)

| Benchmark | DeepSeek V4.1 Flash | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- DeepSeek V4.1 Flash: 55.5 (#29)
- Mistral Medium 3.5: 52.1 (#93)

| Benchmark | DeepSeek V4.1 Flash | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1452 | 1405 |
| LMArena Chinese | 1506 | 1443 |
| LMArena French | 1448 | 1448 |
| LMArena Russian | 1473 | 1396 |
| LMArena Spanish | 1499 | 1406 |
| LMArena German | — | 1453 |
| LMArena Korean | — | 1387 |

## Instruction Following

- DeepSeek V4.1 Flash: 77.6 (#24)
- Mistral Medium 3.5: 74.7 (#87)

| Benchmark | DeepSeek V4.1 Flash | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1475 | 1414 |

## Long Context

- DeepSeek V4.1 Flash: 45.2 (#46)
- Mistral Medium 3.5: 43.2 (#101)

| Benchmark | DeepSeek V4.1 Flash | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1476 | 1414 |

## Writing & Preference

- DeepSeek V4.1 Flash: 65.8 (#43)
- Mistral Medium 3.5: 58.6 (#113)

| Benchmark | DeepSeek V4.1 Flash | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1465 | 1421 |
| LMArena Creative Writing | 1436 | 1372 |
| LMArena Multi-Turn | 1460 | 1423 |
| EQ-Bench Creative Writing | 1540 | — |
| EQ-Bench 4 | — | 993 |

## FAQ

### Is DeepSeek V4.1 Flash better than Mistral Medium 3.5?

DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 39.6 on the Noometry Index.

### Which is cheaper, DeepSeek V4.1 Flash or Mistral Medium 3.5?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is DeepSeek V4.1 Flash or Mistral Medium 3.5 better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 35.7 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 262K.

### How many benchmarks do DeepSeek V4.1 Flash and Mistral Medium 3.5 share?

17 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and Mistral Medium 3.5 has 22.