Qwen2 1.5B Instruct is the compact member of the Qwen2 family — small enough to run on modest hardware, yet capable of following instructions with reasonable coherence for its size. It handles everyday language tasks like summarization, Q&A, and simple reasoning, though it will struggle with complex multi-step problems where larger models have a clear edge. Think of it as a lightweight workhorse suited for constrained environments.
| Benchmark | Score | Type | Recorded |
|---|---|---|---|
| GPQA Diamond | 1.6 | accuracy | 26d ago |
| MuSR | 12.0 | accuracy | 26d ago |
| IFEval | 33.7 | accuracy | 26d ago |
| MMLU-Pro | 16.7 | accuracy | 26d ago |
| BBH | 13.7 | accuracy | 26d ago |
| MATH | 7.2 | accuracy | 26d ago |