# DeepSeek LLM 67B vs Mistral Small

> Mistral Small is the stronger model overall, scoring 33.1 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-mistral-small
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Mistral Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small leads 30.9 to 7.1.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 46.8% for Mistral Small.

## Snapshot

| | DeepSeek LLM 67B | Mistral Small |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 24.8 | 33.1 |
| Rank | 341 | 238 |
| Context | — | 256K |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- Mistral Small: 33.5 (#242)

| Benchmark | DeepSeek LLM 67B | Mistral Small |
|---|---|---|
| LMArena Coding | 1096 | 1363 |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- Mistral Small: 27.9 (#87)

| Benchmark | DeepSeek LLM 67B | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- Mistral Small: 19.3 (#238)

| Benchmark | DeepSeek LLM 67B | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1336 |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| Epoch Capabilities Index | 110.54 | — |
| LiveBench | — | 44% |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- Mistral Small: 15.4 (#287)

| Benchmark | DeepSeek LLM 67B | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 5.8% |
| LMArena Math | 1108 | 1341 |
| MATH Level 5 | 6.4% | 46.8% |
| LiveBench Math | — | 39.9% |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- Mistral Small: 30.9 (#214)

| Benchmark | DeepSeek LLM 67B | Mistral Small |
|---|---|---|
| GPQA Diamond | 24.6% | 47.5% |
| Vectara Hallucination Rate | — | 5.1% |
| LMArena Expert | — | 1293 |
| MMLU | — | 68.7% |

## Multimodal

- DeepSeek LLM 67B: —
- Mistral Small: 32.9 (#91)

| Benchmark | DeepSeek LLM 67B | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- Mistral Small: 45.7 (#164)

| Benchmark | DeepSeek LLM 67B | Mistral Small |
|---|---|---|
| LMArena Non-English | 1073 | 1315 |
| LMArena Chinese | 1132 | 1342 |
| LMArena French | — | 1337 |
| LMArena German | — | 1341 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1260 |
| LMArena Russian | — | 1324 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- Mistral Small: 66.6 (#204)

| Benchmark | DeepSeek LLM 67B | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1079 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- Mistral Small: 40.4 (#151)

| Benchmark | DeepSeek LLM 67B | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1092 | 1327 |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- Mistral Small: 52.6 (#165)

| Benchmark | DeepSeek LLM 67B | Mistral Small |
|---|---|---|
| LMArena Text | 1105 | 1338 |
| LMArena Creative Writing | 1067 | 1304 |
| LMArena Multi-Turn | 1082 | 1344 |
| LiveBench Language | — | 30.5% |

## FAQ

### Is DeepSeek LLM 67B better than Mistral Small?

Mistral Small is the stronger model overall, scoring 33.1 to 24.8 on the Noometry Index.

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

Mistral Small scores higher on coding benchmarks: 33.5 versus 31.3 in the Noometry coding category.

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

13 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Mistral Small has 39.