Qwen2.5 Coder 7B — Benchmarks
Benchmark scores for Qwen2.5 Coder 7B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #20 of 123 open modelscomposite 64/100 across 5 benchmarks in 3 categories · methodology
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| HellaSwag | 76.8% | #20 / 42 | #39 / 76 |
| ARC Challenge | 60.9% | #23 / 51 | #34 / 77 |
| MMLU | 68.0% | #32 / 77 | #73 / 136 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GSM8K | 83.9% | #11 / 60 | #17 / 93 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| WinoGrande | 72.9% | #21 / 46 | #44 / 80 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.