Anthropic: Claude Fable 5.1 (batch)

Anthropic's Claude Fable 5.1, released September 1, 2026, demonstrates competitive response times, ranking in the 41st percentile across benchmarks. However, it is positioned at premium pricing levels, placing in the 4th percentile for cost. A significant strength is its exceptional reliability, achieving a 99% success rate. The model excels in knowledge-based tasks, achieving perfect accuracy in both General Knowledge and Ethics, with the latter also being the most accurate at its price point and speed. It shows strong performance in Instruction Following (88th percentile) and Reasoning (74th percentile), indicating robust cognitive capabilities. Coding performance is also strong at 94% accuracy (79th percentile). While its Hallucinations accuracy is 92% (39th percentile), suggesting room for improvement in acknowledging uncertainty, its overall performance across diverse benchmarks, particularly in complex agentic workflows and knowledge work as highlighted in its description, is impressive.