GPT-4 and Gemini Ultra, respectively, on tests measuring undergraduate-level expert knowledge (MMLU), graduate-level expert reasoning (GPQA) as well as basic mathematics (GSM8k), Anthropic says.
The MMLU test evaluates world knowledge and problem-solving abilities across 57 subjects. Photo courtesy: Anthropic Anthropic highlights that Claude 3 Opus outperformed GPT-4 and Gemini 1.0 Ultra ...
Engineers at Microsoft are reportedly readying data servers for GPT-4.5, which could arrive as early as next week.
OpenAI CEO Sam Altman has announced plans to streamline the company's AI offerings and provided details on the upcoming ...