MoonshotAI: Kimi K2 0905

MoonshotAI's Kimi K2 0905 demonstrates a robust performance profile, particularly excelling in reliability with a 100% success rate across all benchmarks, indicating exceptional stability and minimal technical failures. Its speed performance is moderate, ranking in the 26th percentile, while its pricing is also moderate, falling into the 36th percentile. The model showcases significant strengths in specific areas. It achieves perfect accuracy in Hallucinations (Baseline), demonstrating an impressive ability to acknowledge uncertainty, and performs exceptionally well in Email Classification (99.0% accuracy) and Instruction Following (72.0% accuracy), both ranking in the 84th percentile. Its agentic capabilities are further supported by strong performance in Reasoning (78.0% accuracy, 67th percentile) and Coding (87.0% accuracy, 64th percentile), aligning with its description as optimized for advanced tool use and code synthesis. However, Kimi K2 0905 exhibits notable weaknesses in General Knowledge (77.0% accuracy, 23rd percentile), Ethics (80.0% accuracy, 20th percentile), and Mathematics (53.0% accuracy, 25th percentile), where its accuracy falls into the lower percentiles. While its long-context inference and MoE architecture are advanced, these areas suggest potential for improvement in broader factual recall, ethical discernment, and complex mathematical problem-solving.