# DeepSeek-V3.1 vs Mistral Large

> DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 31.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-mistral-large
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Mistral Large in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 40.9.
- The biggest single-benchmark swing is DTBench: 82.7% for DeepSeek-V3.1 and 65.1% for Mistral Large.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $2 / $6 for Mistral Large.
- DeepSeek-V3.1 accepts more context: 164K tokens versus 131K.

## Snapshot

| | DeepSeek-V3.1 | Mistral Large |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 42.2 | 31.6 |
| Rank | 106 | 258 |
| Context | 164K | 131K |
| Input $/M | $0.25 | $2 |
| Output $/M | $0.95 | $6 |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1: 39.8 (#140)
- Mistral Large: 33.8 (#240)

| Benchmark | DeepSeek-V3.1 | Mistral Large |
|---|---|---|
| LMArena Coding | 1417 | 1277 |
| SciCode | — | 36.2% |
| WeirdML | 38.4% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- DeepSeek-V3.1: —
- Mistral Large: 28.4 (#83)

| Benchmark | DeepSeek-V3.1 | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |

## Reasoning

- DeepSeek-V3.1: 27.3 (#109)
- Mistral Large: 15.4 (#305)

| Benchmark | DeepSeek-V3.1 | Mistral Large |
|---|---|---|
| SimpleBench | 40% | 22.5% |
| LMArena Hard Prompts | 1417 | 1257 |
| DTBench | 82.7% | 65.1% |
| LMCA | 24.3% | 16.7% |
| Epoch Capabilities Index | 139.92 | 128.52 |
| ForecastBench | 58 | 57.1 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LiveBench | — | 48.4% |

## Math

- DeepSeek-V3.1: 36.1 (#125)
- Mistral Large: 17.1 (#285)

| Benchmark | DeepSeek-V3.1 | Mistral Large |
|---|---|---|
| LMArena Math | 1420 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- DeepSeek-V3.1: 43.0 (#86)
- Mistral Large: 30.0 (#224)

| Benchmark | DeepSeek-V3.1 | Mistral Large |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 4.5% |
| LMArena Expert | 1403 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |

## Multilingual

- DeepSeek-V3.1: 51.8 (#100)
- Mistral Large: 40.1 (#214)

| Benchmark | DeepSeek-V3.1 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1400 | 1237 |
| LMArena Chinese | 1470 | 1240 |
| LMArena French | 1447 | 1324 |
| LMArena German | 1412 | 1254 |
| LMArena Japanese | 1374 | 1187 |
| LMArena Korean | 1337 | 1202 |
| LMArena Russian | 1405 | 1257 |
| LMArena Spanish | 1429 | 1268 |

## Instruction Following

- DeepSeek-V3.1: 74.1 (#105)
- Mistral Large: 68.1 (#186)

| Benchmark | DeepSeek-V3.1 | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1400 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |

## Long Context

- DeepSeek-V3.1: 36.3 (#227)
- Mistral Large: 38.3 (#194)

| Benchmark | DeepSeek-V3.1 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1422 | 1262 |
| Fiction.LiveBench | 52.8% | — |

## Writing & Preference

- DeepSeek-V3.1: 60.5 (#93)
- Mistral Large: 40.9 (#237)

| Benchmark | DeepSeek-V3.1 | Mistral Large |
|---|---|---|
| LMArena Text | 1420 | 1266 |
| LMArena Creative Writing | 1401 | 1243 |
| EQ-Bench Creative Writing | 1436 | 985 |
| LMArena Multi-Turn | 1408 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |

## FAQ

### Is DeepSeek-V3.1 better than Mistral Large?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 31.6 on the Noometry Index.

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

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Mistral Large lists at $2 and $6.

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

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 33.8 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek-V3.1 does, with 164K tokens against 131K.

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

24 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Mistral Large has 51.