# DeepSeek LLM 67B vs Mistral Medium 3.5

> Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-mistral-medium-3-5
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Mistral Medium 3.5 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Medium 3.5 leads 39.3 to 7.1.

## Snapshot

| | DeepSeek LLM 67B | Mistral Medium 3.5 |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 24.8 | 39.6 |
| Rank | 341 | 151 |
| Context | — | 262K |
| Input $/M | — | $1.50 |
| Output $/M | — | $7.50 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- Mistral Medium 3.5: 35.7 (#208)

| Benchmark | DeepSeek LLM 67B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Coding | 1096 | 1461 |
| LMArena WebDev | — | 1263 |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- Mistral Medium 3.5: 16.6 (#290)

| Benchmark | DeepSeek LLM 67B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1436 |
| Epoch Capabilities Index | 110.54 | 141.42 |
| Kagi LLM Benchmark | — | 41.4% |
| NYT Connections (extended) | — | 12.9% |
| Chess Puzzles | 0% | — |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- Mistral Medium 3.5: 36.4 (#113)

| Benchmark | DeepSeek LLM 67B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1108 | 1432 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- Mistral Medium 3.5: 39.3 (#123)

| Benchmark | DeepSeek LLM 67B | Mistral Medium 3.5 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1431 |

## Multimodal

- DeepSeek LLM 67B: —
- Mistral Medium 3.5: 37.6 (#64)

| Benchmark | DeepSeek LLM 67B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- Mistral Medium 3.5: 52.1 (#93)

| Benchmark | DeepSeek LLM 67B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1073 | 1405 |
| LMArena Chinese | 1132 | 1443 |
| LMArena French | — | 1448 |
| LMArena German | — | 1453 |
| LMArena Korean | — | 1387 |
| LMArena Russian | — | 1396 |
| LMArena Spanish | — | 1406 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- Mistral Medium 3.5: 74.7 (#87)

| Benchmark | DeepSeek LLM 67B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1414 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- Mistral Medium 3.5: 43.2 (#101)

| Benchmark | DeepSeek LLM 67B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1092 | 1414 |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- Mistral Medium 3.5: 58.6 (#113)

| Benchmark | DeepSeek LLM 67B | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1105 | 1421 |
| LMArena Creative Writing | 1067 | 1372 |
| LMArena Multi-Turn | 1082 | 1423 |
| EQ-Bench 4 | — | 993 |

## FAQ

### Is DeepSeek LLM 67B better than Mistral Medium 3.5?

Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 24.8 on the Noometry Index.

### Is DeepSeek LLM 67B or Mistral Medium 3.5 better for coding?

Mistral Medium 3.5 scores higher on coding benchmarks: 35.7 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Mistral Medium 3.5 share?

11 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Mistral Medium 3.5 has 22.