# Deepseek Coder v2 vs Qwen1.5-7B

> Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-qwen1-5-7b
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Deepseek Coder v2 scores higher in 8 categories and Qwen1.5-7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Deepseek Coder v2 leads 38.4 to 29.8.

## Snapshot

| | Deepseek Coder v2 | Qwen1.5-7B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.3 | 30.8 |
| Rank | 217 | 270 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 37.5 (#178)
- Qwen1.5-7B: 31.6 (#271)

| Benchmark | Deepseek Coder v2 | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1251 | 1107 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 22.6 (#175)
- Qwen1.5-7B: 19.5 (#237)

| Benchmark | Deepseek Coder v2 | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1066 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 32.3 (#188)
- Qwen1.5-7B: 29.0 (#222)

| Benchmark | Deepseek Coder v2 | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1241 | 1080 |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 31.7 (#209)
- Qwen1.5-7B: 28.2 (#239)

| Benchmark | Deepseek Coder v2 | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1181 | 1055 |
| ARC (AI2) Challenge | 64.3% | — |
| MMLU | — | 62.6% |

## Multilingual

- Deepseek Coder v2: 36.4 (#235)
- Qwen1.5-7B: 28.6 (#266)

| Benchmark | Deepseek Coder v2 | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1182 | 1058 |
| LMArena Chinese | 1201 | 1140 |
| LMArena Russian | 1188 | 1006 |
| LMArena French | 1184 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |

## Instruction Following

- Deepseek Coder v2: 61.9 (#237)
- Qwen1.5-7B: 54.4 (#276)

| Benchmark | Deepseek Coder v2 | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1180 | 1058 |

## Long Context

- Deepseek Coder v2: 37.0 (#219)
- Qwen1.5-7B: 33.1 (#261)

| Benchmark | Deepseek Coder v2 | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1219 | 1090 |

## Writing & Preference

- Deepseek Coder v2: 38.4 (#249)
- Qwen1.5-7B: 29.8 (#288)

| Benchmark | Deepseek Coder v2 | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1191 | 1084 |
| LMArena Creative Writing | 1120 | 1035 |
| LMArena Multi-Turn | 1176 | 1061 |

## FAQ

### Is Deepseek Coder v2 better than Qwen1.5-7B?

Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 30.8 on the Noometry Index.

### Is Deepseek Coder v2 or Qwen1.5-7B better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 37.5 versus 31.6 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Qwen1.5-7B share?

12 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen1.5-7B has 13.