# DeepSeek Coder 1.3B vs Qwen-14B

> Qwen-14B has enough public results to be ranked (#275); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-1-3b-vs-qwen-14b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. DeepSeek Coder 1.3B scores higher in 1 category and Qwen-14B in 0 categories, but none of those gaps is larger than the uncertainty.

## Snapshot

| | DeepSeek Coder 1.3B | Qwen-14B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.0 | 31.4 |
| Rank | — | 275 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 1.3B: 31.2 (#287)
- Qwen-14B: 31.2 (#288)

| Benchmark | DeepSeek Coder 1.3B | Qwen-14B |
|---|---|---|
| BigCodeBench Instruct | 22.8% | — |
| LMArena Coding | — | 1071 |
| BigCodeBench Complete | 29.6% | — |
| HumanEval+ | 60.4% | — |
| MBPP+ | 54.8% | — |

## Reasoning

- DeepSeek Coder 1.3B: —
- Qwen-14B: 19.6 (#257)

| Benchmark | DeepSeek Coder 1.3B | Qwen-14B |
|---|---|---|
| Epoch Capabilities Index | 63.6 | 113.03 |
| LMArena Hard Prompts | — | 1027 |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
| WinoGrande | 53.3% | — |

## Math

- DeepSeek Coder 1.3B: —
- Qwen-14B: 31.2 (#227)

| Benchmark | DeepSeek Coder 1.3B | Qwen-14B |
|---|---|---|
| GSM8K | 4.4% | 61.3% |
| LMArena Math | — | 1068 |

## Knowledge

- DeepSeek Coder 1.3B: —
- Qwen-14B: —

| Benchmark | DeepSeek Coder 1.3B | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | 25.4% | 84.4% |
| MMLU | 25.8% | 66.3% |
| BoolQ | — | 86.2% |

## Multilingual

- DeepSeek Coder 1.3B: —
- Qwen-14B: 27.5 (#275)

| Benchmark | DeepSeek Coder 1.3B | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1041 |
| LMArena Chinese | — | 1077 |

## Instruction Following

- DeepSeek Coder 1.3B: —
- Qwen-14B: 52.4 (#289)

| Benchmark | DeepSeek Coder 1.3B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |

## Long Context

- DeepSeek Coder 1.3B: —
- Qwen-14B: 31.3 (#280)

| Benchmark | DeepSeek Coder 1.3B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1028 |

## Writing & Preference

- DeepSeek Coder 1.3B: —
- Qwen-14B: 27.6 (#299)

| Benchmark | DeepSeek Coder 1.3B | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| LMArena Multi-Turn | — | 1022 |

## FAQ

### Is DeepSeek Coder 1.3B better than Qwen-14B?

Qwen-14B has enough public results to be ranked (#275); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 1.3B or Qwen-14B better for coding?

They score almost the same on coding (31.2 vs 31.2); test both on your own repository before choosing.

### How many benchmarks do DeepSeek Coder 1.3B and Qwen-14B share?

4 benchmarks have published results for both models. DeepSeek Coder 1.3B has 9 scored results on Noometry and Qwen-14B has 18.