# Qwen-14B vs Qwen2.5-Coder (1.5B)

> Qwen-14B has enough public results to be ranked (#273); Qwen2.5-Coder (1.5B) does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/qwen-14b-vs-qwen2-5-coder
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both.

## Snapshot

| | Qwen-14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.8 | — |
| Rank | 273 | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Qwen-14B: 30.6 (#283)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Qwen-14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Coding | 1072 | — |

## Reasoning

- Qwen-14B: 18.7 (#255)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Qwen-14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| Epoch Capabilities Index | 112.8 | 112.93 |
| LMArena Hard Prompts | 1027 | — |
| BIG-Bench Hard | 55% | — |
| HellaSwag | — | 76.8% |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
| WinoGrande | — | 72.9% |

## Math

- Qwen-14B: 28.7 (#224)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Qwen-14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| GSM8K | 61.3% | 86.7% |
| LMArena Math | 1068 | — |

## Knowledge

- Qwen-14B: —
- Qwen2.5-Coder (1.5B): —

| Benchmark | Qwen-14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| ARC (AI2) Challenge | 84.4% | 60.9% |
| MMLU | 66.3% | 68% |
| BoolQ | 86.2% | — |

## Multilingual

- Qwen-14B: 27.7 (#270)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Qwen-14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Non-English | 1042 | — |
| LMArena Chinese | 1077 | — |

## Instruction Following

- Qwen-14B: 52.6 (#284)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Qwen-14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Instruction Following | 1031 | — |

## Long Context

- Qwen-14B: 31.3 (#276)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Qwen-14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Longer Query | 1029 | — |

## Writing & Preference

- Qwen-14B: 27.8 (#294)
- Qwen2.5-Coder (1.5B): —

| Benchmark | Qwen-14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| LMArena Text | 1051 | — |
| LMArena Creative Writing | 1028 | — |
| LMArena Multi-Turn | 1022 | — |

## FAQ

### Is Qwen-14B better than Qwen2.5-Coder (1.5B)?

Qwen-14B has enough public results to be ranked (#273); Qwen2.5-Coder (1.5B) does not yet, so treat this comparison as directional.

### How many benchmarks do Qwen-14B and Qwen2.5-Coder (1.5B) share?

4 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Qwen2.5-Coder (1.5B) has 6.