← Voltar às Notícias

Tags: Artificial Analysis

Google Gemini 3 Flash Apresenta Alta Taxa de Alucinação Apesar de Desempenho Líder

Google Gemini 3 Flash Apresenta Alta Taxa de Alucinação Apesar de Desempenho Líder
Google's Gemini 3 Flash model, praised for speed and accuracy, exhibits a striking 91% hallucination rate in tests where it should admit uncertainty. While the model remains top‑scoring in general AI benchmarks, its tendency to fabricate answers when it lacks knowledge raises concerns about reliability, especially as the technology integrates into consumer products like Google Search. Experts highlight the need for better uncertainty detection and caution users to verify AI‑generated information. Ler mais

Seedream 4.0 da ByteDance Supera o Nano Banana do Google em Benchmark de Imagem de IA

Seedream 4.0 da ByteDance Supera o Nano Banana do Google em Benchmark de Imagem de IA
ByteDance, the parent company of TikTok, has launched a new AI image generator called Seedream 4.0. Independent testing by Artificial Analysis shows the model outperforms Google’s Gemini 2.5 Flash, nicknamed Nano Banana, on both text‑to‑image and image‑editing tasks. Seedream 4.0 is available through platforms like fal.ai and Replicate, costing $30 for 1,000 generations, and produces images that many users find indistinguishable from real photos, raising concerns about the future of synthetic media. Ler mais