A compact, conversational model that punches reasonably well for its size, handling everyday language tasks like summarization, Q&A, and simple reasoning with decent fluency. It tends to be straightforward and direct in its responses, though it can struggle with complex multi-step reasoning or nuanced instruction-following that larger models handle more gracefully. Think of it as a reliable workhorse for common text tasks when compute budget is tight.
| Benchmark | Score | Type | Recorded |
|---|---|---|---|
| IFEval | 41.7 | accuracy | 6d ago |