# DeepSeek Coder 6.7B vs Qwen2.5 7B Instruct

> Qwen2.5 7B Instruct has enough public results to be ranked (#314); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-6-7b-vs-qwen2-5-7b-instruct
- 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 0 categories and Qwen2.5 7B Instruct in 1 category, but none of those gaps is larger than the uncertainty.

## Snapshot

| | DeepSeek Coder 6.7B | Qwen2.5 7B Instruct |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.1 | 28.6 |
| Rank | — | 314 |
| Context | — | 131K |
| Input $/M | — | $0.17 |
| Output $/M | — | $0.70 |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 6.7B: 35.2 (#216)
- Qwen2.5 7B Instruct: 35.9 (#204)

| Benchmark | DeepSeek Coder 6.7B | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | 35.5% | 37.6% |
| BigCodeBench Complete | 43.8% | 46.1% |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |

## Agentic & Tool Use

- DeepSeek Coder 6.7B: —
- Qwen2.5 7B Instruct: 23.5 (#117)

| Benchmark | DeepSeek Coder 6.7B | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |

## Reasoning

- DeepSeek Coder 6.7B: —
- Qwen2.5 7B Instruct: 14.3 (#317)

| Benchmark | DeepSeek Coder 6.7B | Qwen2.5 7B Instruct |
|---|---|---|
| Epoch Capabilities Index | 88.88 | 118.44 |
| Chess Puzzles | — | 0% |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| WinoGrande | 57.6% | — |

## Math

- DeepSeek Coder 6.7B: —
- Qwen2.5 7B Instruct: 11.8 (#300)

| Benchmark | DeepSeek Coder 6.7B | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
| GSM8K | 21.3% | — |

## Knowledge

- DeepSeek Coder 6.7B: —
- Qwen2.5 7B Instruct: 17.0 (#281)

| Benchmark | DeepSeek Coder 6.7B | Qwen2.5 7B Instruct |
|---|---|---|
| MMLU | 36.4% | 72.9% |
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| ARC (AI2) Challenge | 36.4% | — |

## Instruction Following

- DeepSeek Coder 6.7B: —
- Qwen2.5 7B Instruct: 63.4 (#226)

| Benchmark | DeepSeek Coder 6.7B | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |

## Writing & Preference

- DeepSeek Coder 6.7B: —
- Qwen2.5 7B Instruct: 48.8 (#194)

| Benchmark | DeepSeek Coder 6.7B | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | — | 73.1% |

## FAQ

### Is DeepSeek Coder 6.7B better than Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct has enough public results to be ranked (#314); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 6.7B or Qwen2.5 7B Instruct better for coding?

They score almost the same on coding (35.2 vs 35.9); test both on your own repository before choosing.

### How many benchmarks do DeepSeek Coder 6.7B and Qwen2.5 7B Instruct share?

4 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Qwen2.5 7B Instruct has 15.