# Qwen2.5-Coder (1.5B) vs Qwen3.5-9B

> Qwen3.5-9B has enough public results to be ranked (#235); Qwen2.5-Coder (1.5B) does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/qwen2-5-coder-vs-qwen3-5-9b
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both.

## Snapshot

| | Qwen2.5-Coder (1.5B) | Qwen3.5-9B |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | — | 33.3 |
| Rank | — | 235 |
| Context | — | 262K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.15 |
| Weights | Open | Open |

## Coding

- Qwen2.5-Coder (1.5B): —
- Qwen3.5-9B: 35.3 (#213)

| Benchmark | Qwen2.5-Coder (1.5B) | Qwen3.5-9B |
|---|---|---|
| SciCode | — | 27.5% |

## Agentic & Tool Use

- Qwen2.5-Coder (1.5B): —
- Qwen3.5-9B: 14.4 (#143)

| Benchmark | Qwen2.5-Coder (1.5B) | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |

## Reasoning

- Qwen2.5-Coder (1.5B): —
- Qwen3.5-9B: 22.5 (#178)

| Benchmark | Qwen2.5-Coder (1.5B) | Qwen3.5-9B |
|---|---|---|
| Epoch Capabilities Index | 112.93 | 139.45 |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 12% |
| DTBench | — | 71.2% |
| LMCA | — | 24.5% |
| HellaSwag | 76.8% | — |
| WinoGrande | 72.9% | — |

## Math

- Qwen2.5-Coder (1.5B): —
- Qwen3.5-9B: 33.5 (#174)

| Benchmark | Qwen2.5-Coder (1.5B) | Qwen3.5-9B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 48.5% |
| OTIS Mock AIME 2024-2025 | — | 61.7% |
| GSM8K | 86.7% | — |

## Knowledge

- Qwen2.5-Coder (1.5B): —
- Qwen3.5-9B: 46.0 (#77)

| Benchmark | Qwen2.5-Coder (1.5B) | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | — | 79% |
| ARC (AI2) Challenge | 60.9% | — |
| MMLU | 68% | — |

## FAQ

### Is Qwen2.5-Coder (1.5B) better than Qwen3.5-9B?

Qwen3.5-9B has enough public results to be ranked (#235); Qwen2.5-Coder (1.5B) does not yet, so treat this comparison as directional.

### How many benchmarks do Qwen2.5-Coder (1.5B) and Qwen3.5-9B share?

1 benchmark has published results for both models. Qwen2.5-Coder (1.5B) has 6 scored results on Noometry and Qwen3.5-9B has 10.