DeepSeek V4 Models Show Similar Evaluation Results

Teortaxes, known for promoting DeepSeek, shared a detailed comparison of the company's V4 models. According to the post, these updated models reach nearly identical standings on various third party evaluations. The commentary highlights that results align closely with those from Flash-0731 while suggesting similar computational resources are involved. The author questions the value provided by substantially larger parameter counts in the latest iterations, noting a lack of clear gains from the added scale.