Arcee AI: Virtuoso Large

Arcee AI's Virtuoso-Large, a 72B parameter LLM, demonstrates strong overall performance, particularly excelling in speed and reliability. It consistently ranks among the fastest models, achieving the 93rd percentile across six benchmarks, and offers competitive pricing, placing in the 44th percentile. Notably, its reliability is exceptional, with a perfect 100th percentile ranking, indicating minimal technical failures and consistent response delivery. Across specific benchmarks, Virtuoso-Large shows a balanced profile. It achieved perfect accuracy in Ethics and near-perfect scores in Email Classification (99.0%) and General Knowledge (99.5%), often being the most accurate among models of comparable speed. Its Instruction Following capabilities are strong at 63.0% accuracy, securing the top spot for speed in this category. While its Coding (84.0%) and Reasoning (72.0%) scores are solid, they are not its absolute strongest areas, though still competitive. The model's 128k context length, inherited from Qwen 2.5, is a significant strength, enabling it to process extensive documents. Despite its size, aggressive KV-cache optimizations ensure practical production-grade latency. Virtuoso-Large is positioned as a robust "fallback" brain for complex enterprise tasks.