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.
More from Models
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11