Claude Fable 5.1 made me a really nice animated pelican
Claude Fable 5.1 sets a new standard with impressive benchmark scores.
“Fable 5.1 "sets a new standard for coding, knowledge work, and long-running problem-solving tasks".”
Anthropic announced Claude Fable 5.1, which achieved a score of 52.6% on the new Terminal-Bench-Science benchmark, significantly improving from its predecessor. This upgrade aims to enhance capabilities in coding and problem-solving tasks, indicating a notable advancement in AI model performance.