# DeepSeek V4 Flash vs Mistral Small 3

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 31.2 on the Noometry Index. Mistral Small 3 costs 4.6× less per token, which makes it the better buy when DeepSeek V4 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v4-flash-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Mistral Small 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Flash leads 60.3 to 16.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.4% for DeepSeek V4 Flash and 6.7% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4 Flash.
- DeepSeek V4 Flash accepts more context: 1M tokens versus 33K.

## Snapshot

| | DeepSeek V4 Flash | Mistral Small 3 |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 53.6 | 31.2 |
| Rank | 35 | 278 |
| Context | 1M | 33K |
| Input $/M | $0.15 | $0.05 |
| Output $/M | $0.60 | $0.08 |
| Weights | Open | Open |

## Coding

- DeepSeek V4 Flash: 47.9 (#59)
- Mistral Small 3: 36.5 (#207)

| Benchmark | DeepSeek V4 Flash | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1457 | 1246 |
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 1,306 | — |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#30)
- Mistral Small 3: 18.9 (#273)

| Benchmark | DeepSeek V4 Flash | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 33% | 0% |
| LMArena Hard Prompts | 1444 | 1233 |
| Epoch Capabilities Index | 154.49 | 127.07 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |

## Math

- DeepSeek V4 Flash: 60.3 (#37)
- Mistral Small 3: 16.3 (#295)

| Benchmark | DeepSeek V4 Flash | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.4% | 6.7% |
| LMArena Math | 1427 | 1240 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| ProofBench | 56% | — |

## Knowledge

- DeepSeek V4 Flash: 55.4 (#48)
- Mistral Small 3: 25.1 (#263)

| Benchmark | DeepSeek V4 Flash | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 91% | 47.3% |
| LMArena Expert | 1441 | 1202 |
| SimpleQA Verified | 33.6% | — |
| Confabulations | — | 25.2% |

## Multilingual

- DeepSeek V4 Flash: 53.0 (#72)
- Mistral Small 3: 37.3 (#236)

| Benchmark | DeepSeek V4 Flash | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1420 | 1198 |
| LMArena Chinese | 1468 | 1204 |
| LMArena French | 1439 | 1203 |
| LMArena German | 1418 | 1211 |
| LMArena Japanese | 1406 | 1111 |
| LMArena Korean | 1384 | 1188 |
| LMArena Russian | 1428 | 1216 |
| LMArena Spanish | 1436 | — |

## Instruction Following

- DeepSeek V4 Flash: 74.9 (#81)
- Mistral Small 3: 63.7 (#229)

| Benchmark | DeepSeek V4 Flash | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1421 | 1214 |

## Long Context

- DeepSeek V4 Flash: 43.8 (#85)
- Mistral Small 3: 37.8 (#211)

| Benchmark | DeepSeek V4 Flash | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1434 | 1246 |

## Writing & Preference

- DeepSeek V4 Flash: 63.8 (#61)
- Mistral Small 3: 32.2 (#280)

| Benchmark | DeepSeek V4 Flash | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1432 | 1234 |
| LMArena Creative Writing | 1403 | 1195 |
| EQ-Bench Creative Writing | 1559 | 707 |
| LMArena Multi-Turn | 1449 | 1217 |

## FAQ

### Is DeepSeek V4 Flash better than Mistral Small 3?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 31.2 on the Noometry Index. Mistral Small 3 costs 4.6× less per token, which makes it the better buy when DeepSeek V4 Flash's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek V4 Flash or Mistral Small 3?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; DeepSeek V4 Flash lists at $0.15 and $0.60.

### Is DeepSeek V4 Flash or Mistral Small 3 better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 36.5 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4 Flash does, with 1M tokens against 33K.

### How many benchmarks do DeepSeek V4 Flash and Mistral Small 3 share?

21 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Mistral Small 3 has 24.