# DeepSeek Coder 6.7B vs DeepSeek LLM 67B

> DeepSeek LLM 67B has enough public results to be ranked (#347); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-6-7b-vs-deepseek-llm-67b
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. DeepSeek Coder 6.7B scores higher in 1 category and DeepSeek LLM 67B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 6.7B leads 35.8 to 31.9.

## Snapshot

| | DeepSeek Coder 6.7B | DeepSeek LLM 67B |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 37.6 | 24.9 |
| Rank | — | 347 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 6.7B: 35.8 (#219)
- DeepSeek LLM 67B: 31.9 (#278)

| Benchmark | DeepSeek Coder 6.7B | DeepSeek LLM 67B |
|---|---|---|
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 1096 |
| BigCodeBench Complete | 43.8% | — |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |

## Reasoning

- DeepSeek Coder 6.7B: —
- DeepSeek LLM 67B: 16.5 (#304)

| Benchmark | DeepSeek Coder 6.7B | DeepSeek LLM 67B |
|---|---|---|
| Epoch Capabilities Index | 89.62 | 110.5 |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1070 |
| WinoGrande | 57.6% | — |

## Math

- DeepSeek Coder 6.7B: —
- DeepSeek LLM 67B: 8.7 (#324)

| Benchmark | DeepSeek Coder 6.7B | DeepSeek LLM 67B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0.8% |
| LMArena Math | — | 1108 |
| MATH Level 5 | — | 6.4% |
| GSM8K | 21.3% | — |

## Knowledge

- DeepSeek Coder 6.7B: —
- DeepSeek LLM 67B: 7.0 (#313)

| Benchmark | DeepSeek Coder 6.7B | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | — | 24.6% |
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |

## Multilingual

- DeepSeek Coder 6.7B: —
- DeepSeek LLM 67B: 29.4 (#267)

| Benchmark | DeepSeek Coder 6.7B | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | — | 1073 |
| LMArena Chinese | — | 1132 |

## Instruction Following

- DeepSeek Coder 6.7B: —
- DeepSeek LLM 67B: 55.4 (#277)

| Benchmark | DeepSeek Coder 6.7B | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | — | 1079 |

## Long Context

- DeepSeek Coder 6.7B: —
- DeepSeek LLM 67B: 33.1 (#265)

| Benchmark | DeepSeek Coder 6.7B | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | — | 1092 |

## Writing & Preference

- DeepSeek Coder 6.7B: —
- DeepSeek LLM 67B: 31.6 (#282)

| Benchmark | DeepSeek Coder 6.7B | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | — | 1105 |
| LMArena Creative Writing | — | 1067 |
| LMArena Multi-Turn | — | 1082 |

## FAQ

### Is DeepSeek Coder 6.7B better than DeepSeek LLM 67B?

DeepSeek LLM 67B has enough public results to be ranked (#347); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 6.7B or DeepSeek LLM 67B better for coding?

DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.8 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek Coder 6.7B and DeepSeek LLM 67B share?

1 benchmark has published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and DeepSeek LLM 67B has 15.