Найдено 1 материалов по запросу «LLM benchmarks»
По релевантностиПо дате
LLMTechCrunch
DeepSeek unveiled new AI models and claimed to have nearly closed the gap with market leaders
DeepSeek presented preliminary versions of two new AI models, claiming better efficiency, improved performance relative to V3.2, and a nearly closed gap with flagship models in reasoning tasks.