Anthropic: Claude Sonnet 4.6

Anthropic's Claude Sonnet 4.6, created on Feb 17, 2026, demonstrates competitive response times, ranking in the 58th percentile across benchmarks. However, it is positioned at a premium price point, falling into the 13th percentile for cost. A standout feature is its exceptional reliability, achieving a perfect 100% success rate across all evaluated benchmarks, indicating robust technical stability. Sonnet 4.6 exhibits frontier performance across several key areas. It achieved perfect accuracy in both General Knowledge and Ethics, with the latter also being the most accurate model at its price point and speed. Its Coding and Mathematics capabilities are strong, scoring 94% accuracy and ranking in the 88th and 82nd percentiles respectively. The model also shows strong reasoning abilities (88% accuracy) and solid instruction following (70% accuracy). While its Email Classification (97% accuracy) is good, it ranks in the 42nd percentile, suggesting room for improvement relative to peers. Its hallucination rate is commendably low at 98% accuracy. Overall, Sonnet 4.6 excels in complex cognitive tasks and professional applications, making it highly suitable for iterative development, project management, and polished document creation.