# DeepSeek LLM 67B vs Mistral Large 4

> Mistral Large 4 is the stronger model overall, scoring 43.1 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-mistral-large-4
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Mistral Large 4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Large 4 leads 40.4 to 8.7.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek LLM 67B | Mistral Large 4 |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 24.9 | 43.1 |
| Rank | 347 | 99 |
| Context | — | 1.05M |
| Input $/M | — | $0.68 |
| Output $/M | — | $2.09 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- Mistral Large 4: 48.6 (#57)

| Benchmark | DeepSeek LLM 67B | Mistral Large 4 |
|---|---|---|
| LMArena Coding | 1096 | 1475 |
| LMArena WebDev | — | 1541 |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- Mistral Large 4: 22.5 (#192)

| Benchmark | DeepSeek LLM 67B | Mistral Large 4 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1444 |
| NYT Connections (extended) | — | 27.4% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- Mistral Large 4: 40.4 (#91)

| Benchmark | DeepSeek LLM 67B | Mistral Large 4 |
|---|---|---|
| LMArena Math | 1108 | 1488 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- Mistral Large 4: 36.6 (#166)

| Benchmark | DeepSeek LLM 67B | Mistral Large 4 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| SimpleQA Verified | — | 20% |
| LMArena Expert | — | 1447 |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- Mistral Large 4: 52.6 (#82)

| Benchmark | DeepSeek LLM 67B | Mistral Large 4 |
|---|---|---|
| LMArena Non-English | 1073 | 1415 |
| LMArena Chinese | 1132 | 1491 |
| LMArena Russian | — | 1414 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- Mistral Large 4: 75.0 (#76)

| Benchmark | DeepSeek LLM 67B | Mistral Large 4 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1424 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- Mistral Large 4: 43.6 (#89)

| Benchmark | DeepSeek LLM 67B | Mistral Large 4 |
|---|---|---|
| LMArena Longer Query | 1092 | 1429 |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- Mistral Large 4: 60.4 (#97)

| Benchmark | DeepSeek LLM 67B | Mistral Large 4 |
|---|---|---|
| LMArena Text | 1105 | 1427 |
| LMArena Creative Writing | 1067 | 1361 |
| LMArena Multi-Turn | 1082 | 1424 |

## FAQ

### Is DeepSeek LLM 67B better than Mistral Large 4?

Mistral Large 4 is the stronger model overall, scoring 43.1 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or Mistral Large 4 better for coding?

Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Mistral Large 4 share?

10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Mistral Large 4 has 15.