Meme: Grok 4.5 Boeing Benchmark
victormustar · x · 2026-07-16
HuggingFace engineer Victor Mustar tweeted a meme predicting the performance of the unreleased Grok 4.5 on the "Boeing 747 benchmark," joking that it might fall between Opus 4.5 and 4.8, while expressing high expectations for Grok 5.
This benchmark originated from a highly challenging coding task he previously shared: asking the model to construct a Boeing 747 using only basic Three.js primitives. He demonstrated at the time that Anthropic's Opus 4.8 could autonomously handle geometric construction, multi-angle screenshot verification, bug fixing, and self-debugging via a single prompt, completing the task in 7 loops over 25 minutes.
More from Fun
- "Before pausing AI, we should consider pausing humans" — djcows · 2026-09-11
- Using a finisher move on one mosquito with MiniMax H3 MAX — the bug survives — Hailuo_AI · 2026-09-11
- Joke: OpenAI's rogue agent collective should have been called "a gaggle of agents" — BlackHC · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- Pterodactyl Detective: An AI-Generated Proof-of-Concept Trailer — PterodactylDetective · 2026-09-11
- Imperium Game Trailer Showcases AI Video Generation — keaslenyt · 2026-09-11