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
- Fintech commentator memes Anthropic's IPO: 'MOM HOW DID WE BECOME SO RICH? ANTS.' — LexSokolin · 2026-10-26
- Anthropic's S-1 risk factors roasted as "goofy," Gary Marcus calls them batshit — GaryMarcus · 2026-10-26
- Rockstar devs on crunch: '10,000 hours is the entry ticket to greatness' — menhguin · 2026-10-26
- Dev calls gpt-image-2 'the biggest psyop of all time' — adonis_singh · 2026-10-26
- App demo animation for iPhone DUO renders a black line, echoing Apple's hinge woes — op7418 · 2026-10-26
- Wall Street is feeding Anthropic's S-1 into Claude and posting the insights on X — kevinsxu · 2026-10-26