DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark

ayushtweetshere · x · 2026-09-11

OpenDesignHQ benchmarked DeepSeek V4.1 Flash on everyday design tasks based on user requests and found it reached 98% of GPT-6 Astra's score at just 1.4% of the cost. According to the results, every model except Astra scored lower while costing more, raising the question of whether open models are overtaking closed ones. The post's amplifier argues Chinese open-source models leave no moat for US labs.

Original post →

More from Models

Models channel →