"Alphabet’s testing has shown that its Gemini 3 model, released last fall, scored 72.1 per cent on a benchmark that measures factual accuracy. While the company hailed the performance as state-of-the-art, it translates into an error rate of roughly 28 per cent."
"Alphabet’s testing has shown that its Gemini 3 model, released last fall, scored 72.1 per cent on a benchmark that measures factual accuracy. While the company hailed the performance as state-of-the-art, it translates into an error rate of roughly 28 per cent."