# DeepSeek V4 Flash vs Mistral

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 29.4 on the Noometry Index.

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

## Summary

- They share 17 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Mistral in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Flash leads 60.0 to 20.5.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Flash | Mistral |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 53.6 | 29.4 |
| Rank | 32 | 297 |
| Context | 1M | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Flash: 47.6 (#56)
- Mistral: 33.2 (#249)

| Benchmark | DeepSeek V4 Flash | Mistral |
|---|---|---|
| LMArena Coding | 1457 | 1162 |
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1581 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#25)
- Mistral: 21.3 (#199)

| Benchmark | DeepSeek V4 Flash | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1149 |
| 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% | — |
| Chess Puzzles | 33% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |
| Epoch Capabilities Index | 154.51 | — |

## Math

- DeepSeek V4 Flash: 60.0 (#31)
- Mistral: 20.5 (#275)

| Benchmark | DeepSeek V4 Flash | Mistral |
|---|---|---|
| LMArena Math | 1427 | 1180 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 56% | — |
| Omni-MATH | — | 7.2% |

## Knowledge

- DeepSeek V4 Flash: 55.5 (#43)
- Mistral: 16.3 (#283)

| Benchmark | DeepSeek V4 Flash | Mistral |
|---|---|---|
| LMArena Expert | 1441 | 1125 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |

## Multilingual

- DeepSeek V4 Flash: 53.2 (#71)
- Mistral: 33.0 (#249)

| Benchmark | DeepSeek V4 Flash | Mistral |
|---|---|---|
| LMArena Non-English | 1420 | 1129 |
| LMArena Chinese | 1467 | 1109 |
| LMArena French | 1438 | 1179 |
| LMArena German | 1418 | 1155 |
| LMArena Japanese | 1403 | 1012 |
| LMArena Korean | 1383 | 1032 |
| LMArena Russian | 1428 | 1168 |
| LMArena Spanish | 1437 | 1143 |

## Instruction Following

- DeepSeek V4 Flash: 75.1 (#76)
- Mistral: 52.9 (#283)

| Benchmark | DeepSeek V4 Flash | Mistral |
|---|---|---|
| LMArena Instruction Following | 1421 | 1152 |
| IFEval | — | 56.8% |

## Long Context

- DeepSeek V4 Flash: 43.8 (#81)
- Mistral: 35.0 (#240)

| Benchmark | DeepSeek V4 Flash | Mistral |
|---|---|---|
| LMArena Longer Query | 1435 | 1154 |

## Writing & Preference

- DeepSeek V4 Flash: 64.0 (#59)
- Mistral: 37.2 (#255)

| Benchmark | DeepSeek V4 Flash | Mistral |
|---|---|---|
| LMArena Text | 1432 | 1165 |
| LMArena Creative Writing | 1403 | 1158 |
| LMArena Multi-Turn | 1449 | 1147 |
| EQ-Bench Creative Writing | 1559 | — |
| WildBench | — | 66% |

## FAQ

### Is DeepSeek V4 Flash better than Mistral?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 29.4 on the Noometry Index.

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

DeepSeek V4 Flash scores higher on coding benchmarks: 47.6 versus 33.2 in the Noometry coding category.

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

17 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Mistral has 22.