Google Gemini 3.6 Flash

Inception's Mercury-2, a diffusion-based large language model, outperformed Google's Gemini 3.6 Flash, an autoregressive model, in latency and cost across agentic workflows, achieving 0.00s time-to-fi…

Kimi K3 defeated Google Gemini 3.6 Flash 115.0 to 106.0 in a head-to-head text task evaluation, with 94% confidence, according to a benchmark run by an unnamed tester using 12 fresh tasks scored by GP…