Qwen2.5 Coder 32B Instruct — Benchmarks
Benchmark scores for Qwen2.5 Coder 32B Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SWE-bench Verified | 47.0% | #11 / 13 | #105 / 163 |
| SWE-bench Bash Only | 9.0% | #9 / 9 | #48 / 48 |
| Aider Polyglot | 16.4% | #14 / 18 | #61 / 69 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GSM8K | 93.0% | #3 / 59 | #3 / 93 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.