Create a thread about the "Gemini 2.5 Research Report" for a scientific audience. Keep a scientific tone that sparks curiosity.

Gemini 2.5 brings models for complex AI tasks. Pro is described as the family’s most capable, with strengths in coding, reasoning and multimodal understanding. It can process up to three hours of video and input sequences of up to 1 million tokens, surpassing Gemini 1.5 Pro. The Gemini 2.X series supports native multimodality, tool use and inputs exceeding 1 million tokens. Gemini 2.5 Flash offers reasoning with lower compute and latency, extending the lineup across capability and cost.

1/6