# DeepSeek LLM 67B vs Ministral 3B

> Ministral 3B is the stronger model overall, scoring 26.2 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-ministral-3b
- Last updated: 2026-10-12
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Ministral 3B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Ministral 3B leads 26.6 to 8.7.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 14.4% for Ministral 3B.

## Snapshot

| | DeepSeek LLM 67B | Ministral 3B |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 24.9 | 26.2 |
| Rank | 347 | 338 |
| Context | — | 131K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.10 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- Ministral 3B: —

| Benchmark | DeepSeek LLM 67B | Ministral 3B |
|---|---|---|
| LMArena Coding | 1096 | — |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- Ministral 3B: 18.4 (#282)

| Benchmark | DeepSeek LLM 67B | Ministral 3B |
|---|---|---|
| Epoch Capabilities Index | 110.5 | 118.1 |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1070 | — |
| DTBench | — | 51.7% |
| LMCA | — | 5.5% |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- Ministral 3B: 26.6 (#258)

| Benchmark | DeepSeek LLM 67B | Ministral 3B |
|---|---|---|
| MATH Level 5 | 6.4% | 14.4% |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- Ministral 3B: 10.4 (#302)

| Benchmark | DeepSeek LLM 67B | Ministral 3B |
|---|---|---|
| GPQA Diamond | 24.6% | 25.3% |
| Vectara Hallucination Rate | — | 7.3% |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- Ministral 3B: —

| Benchmark | DeepSeek LLM 67B | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- Ministral 3B: —

| Benchmark | DeepSeek LLM 67B | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1079 | — |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- Ministral 3B: —

| Benchmark | DeepSeek LLM 67B | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1092 | — |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- Ministral 3B: —

| Benchmark | DeepSeek LLM 67B | Ministral 3B |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |

## FAQ

### Is DeepSeek LLM 67B better than Ministral 3B?

Ministral 3B is the stronger model overall, scoring 26.2 to 24.9 on the Noometry Index.

### How many benchmarks do DeepSeek LLM 67B and Ministral 3B share?

3 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Ministral 3B has 6.