Anthropic reported that Claude Opus 5.5, Sonnet 5.5, and Haiku 5.5 scored 99% on the company's internal political evenhandedness evaluation.

Overview Debates Related claims Topics Sources

AI research & benchmarks

AI research advances and the benchmarks used to measure progress.

1,209 claims·193 news stories

AI assistants & chatbots

756 claims·259 news stories

AI bias & fairness

49 claims·19 news stories