OpenAI and Anthropic models share a favorite name, writing benchmark finds
almmaasoglu · x · 2026-09-07
A favorite finding from Felda AI's writing benchmark: both OpenAI and Anthropic models love to use the same name. Each dot covers 20 outputs, with lines connecting the same prompt groups across models, visualizing the naming-preference distribution. The full official benchmark is coming soon.
More from Models
- GPT-6 Astra Turns Van Gogh's Starry Night Into a Walkable 3D World — emmanuelvivier · 2026-09-07
- User Test: Astra Burned 33% of Its 5-Hour Limit in Just 1 Prompt, 3 Projects — ChrisUniverse · 2026-09-07
- ~1000x Price Collapse in 18 Months: GLM-5.3 Flash Beats o1 Pro at 1/1000 the Cost — MaziyarPanahi · 2026-09-07
- Dev compiles early GPT-6 Astra demos from launch day into one thread — thisiskp_ · 2026-09-07
- Intelligence per Dollar Collapsed ~1000x in 1.5 Years: o1 Pro to GLM-5.3 Flash — Yuchenj_UW · 2026-09-07
- Dev tests GPT-6 Astra's voice latency and comes away calling it AGI — BLUECOW009 · 2026-09-07