Arcee AI: Virtuoso Large

Arcee AI: Virtuoso Large is a 72B parameter, top-tier general-purpose LLM designed for cross-domain reasoning, creative writing, and enterprise QA. It boasts an impressive 128k context length, inherited from Qwen 2.5, enabling it to process extensive documents. The model demonstrates exceptional reliability with a 99% success rate across benchmarks, consistently providing usable responses. Virtuoso Large performs among the fastest models, ranking in the 91st percentile for speed, and offers competitive pricing, placing it in the 49th percentile. Key strengths include perfect accuracy in Hallucinations and Ethics benchmarks, where it also stands out as the most accurate model at its price point and speed. It shows strong performance in General Knowledge (99.5% accuracy) and Email Classification (99.0% accuracy), being the most accurate among models of comparable speed in the latter. While its Instruction Following (63.0%) and Reasoning (74.0%) capabilities are solid, its Mathematics performance (79.0%) is a notable weakness, ranking in the 34th percentile. Despite this, its aggressive KV-cache optimizations ensure low-second first-token latency, making it a practical production-grade solution, particularly as a "fallback" brain in Conductor pipelines.