# Qwen2.5 32B Instruct vs StarCoder 2 15B

> Qwen2.5 32B Instruct has enough public results to be ranked (#297); StarCoder 2 15B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/qwen2-5-32b-instruct-vs-starcoder-2-15b
- Last updated: 2026-10-11
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Qwen2.5 32B Instruct scores higher in 1 category and StarCoder 2 15B in 0 categories; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 52.3% for Qwen2.5 32B Instruct and 38.4% for StarCoder 2 15B.

## Snapshot

| | Qwen2.5 32B Instruct | StarCoder 2 15B |
|---|---|---|
| Provider | Alibaba (Qwen) | NVIDIA |
| Noometry Index | 30.1 | 38.1 |
| Rank | 297 | — |
| Context | 131K | — |
| Input $/M | $0.70 | — |
| Output $/M | $2.80 | — |
| Weights | Open | Open |

## Coding

- Qwen2.5 32B Instruct: 38.7 (#169)
- StarCoder 2 15B: 36.6

| Benchmark | Qwen2.5 32B Instruct | StarCoder 2 15B |
|---|---|---|
| BigCodeBench Complete | 52.3% | 38.4% |
| BigCodeBench Instruct | 45% | — |
| HumanEval+ | — | 37.8% |

## Reasoning

- Qwen2.5 32B Instruct: 19.2 (#266)
- StarCoder 2 15B: —

| Benchmark | Qwen2.5 32B Instruct | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 128.52 | 105 |
| Chess Puzzles | 0% | — |
| WinoGrande | — | 64.3% |

## Math

- Qwen2.5 32B Instruct: 16.2 (#296)
- StarCoder 2 15B: —

| Benchmark | Qwen2.5 32B Instruct | StarCoder 2 15B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.4% | — |
| MATH Level 5 | 56.1% | — |
| GSM8K | — | 57.7% |

## Knowledge

- Qwen2.5 32B Instruct: 24.9 (#266)
- StarCoder 2 15B: —

| Benchmark | Qwen2.5 32B Instruct | StarCoder 2 15B |
|---|---|---|
| GPQA Diamond | 46.1% | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |

## FAQ

### Is Qwen2.5 32B Instruct better than StarCoder 2 15B?

Qwen2.5 32B Instruct has enough public results to be ranked (#297); StarCoder 2 15B does not yet, so treat this comparison as directional.

### Is Qwen2.5 32B Instruct or StarCoder 2 15B better for coding?

Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.7 versus 36.6 in the Noometry coding category.

### How many benchmarks do Qwen2.5 32B Instruct and StarCoder 2 15B share?

2 benchmarks have published results for both models. Qwen2.5 32B Instruct has 7 scored results on Noometry and StarCoder 2 15B has 7.