Ina Fried / Axios:Anthropic open sources a method to score AI model political evenhandedness; Gemini 2.5 Pro got 97%, Grok 4 96%, Claude Opus 4.1 95%, GPT-5 89%, and Llama 4 66% — Anthropic is releasing an open source method to evaluate the political “evenhandedness” of AI chatbots, the company said Thursday.