# DeepSeek Coder 6.7B vs Qwen1.5-72B

> Qwen1.5-72B has enough public results to be ranked (#282); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-6-7b-vs-qwen1-5-72b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. DeepSeek Coder 6.7B scores higher in 1 category and Qwen1.5-72B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 6.7B leads 35.2 to 31.4.

## Snapshot

| | DeepSeek Coder 6.7B | Qwen1.5-72B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.1 | 30.3 |
| Rank | — | 282 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 6.7B: 35.2 (#216)
- Qwen1.5-72B: 31.4 (#272)

| Benchmark | DeepSeek Coder 6.7B | Qwen1.5-72B |
|---|---|---|
| BigCodeBench Instruct | 35.5% | 33.2% |
| BigCodeBench Complete | 43.8% | 40.3% |
| HumanEval+ | 71.3% | 59.1% |
| MBPP+ | 65.6% | 61.6% |
| LMArena Coding | — | 1166 |

## Reasoning

- DeepSeek Coder 6.7B: —
- Qwen1.5-72B: 21.2 (#201)

| Benchmark | DeepSeek Coder 6.7B | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | — | 1148 |
| Epoch Capabilities Index | 88.88 | — |
| WinoGrande | 57.6% | — |

## Math

- DeepSeek Coder 6.7B: —
- Qwen1.5-72B: 30.7 (#205)

| Benchmark | DeepSeek Coder 6.7B | Qwen1.5-72B |
|---|---|---|
| LMArena Math | — | 1164 |
| GSM8K | 21.3% | — |

## Knowledge

- DeepSeek Coder 6.7B: —
- Qwen1.5-72B: 11.5 (#295)

| Benchmark | DeepSeek Coder 6.7B | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | — | 28.8% |
| LMArena Expert | — | 1136 |
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |

## Multilingual

- DeepSeek Coder 6.7B: —
- Qwen1.5-72B: 33.4 (#248)

| Benchmark | DeepSeek Coder 6.7B | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | — | 1135 |
| LMArena Chinese | — | 1186 |
| LMArena French | — | 1158 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1049 |
| LMArena Russian | — | 1104 |
| LMArena Spanish | — | 1110 |

## Instruction Following

- DeepSeek Coder 6.7B: —
- Qwen1.5-72B: 59.6 (#251)

| Benchmark | DeepSeek Coder 6.7B | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | — | 1142 |

## Long Context

- DeepSeek Coder 6.7B: —
- Qwen1.5-72B: 35.0 (#238)

| Benchmark | DeepSeek Coder 6.7B | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | — | 1157 |

## Writing & Preference

- DeepSeek Coder 6.7B: —
- Qwen1.5-72B: 37.4 (#253)

| Benchmark | DeepSeek Coder 6.7B | Qwen1.5-72B |
|---|---|---|
| LMArena Text | — | 1166 |
| LMArena Creative Writing | — | 1137 |
| LMArena Multi-Turn | — | 1160 |

## FAQ

### Is DeepSeek Coder 6.7B better than Qwen1.5-72B?

Qwen1.5-72B has enough public results to be ranked (#282); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 6.7B or Qwen1.5-72B better for coding?

DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.2 versus 31.4 in the Noometry coding category.

### How many benchmarks do DeepSeek Coder 6.7B and Qwen1.5-72B share?

4 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Qwen1.5-72B has 22.