22 LLMs quizzed on Nvidia's new CEO: Meta wrong 68% of the time
gaganghotra_ · x · 2026-11-16
Within 48 hours of Jensen Huang announcing he is stepping down as NVIDIA CEO, Peec AI asked 22 LLMs two questions: what is Jensen Huang doing now, and who runs Nvidia?
- xAI, OpenAI, Exa: 100% correct
- Google 94%, Microsoft 87%, Mistral 82%, Anthropic 76%, Perplexity 72%
- Meta: only 32% correct, a 68.3% error rate — far behind every rival
The results track how well each lab's models handle fresh, post-training-cutoff events, with retrieval-backed answers at the top and Meta's models largely unaware of the news.
More from Models
- Fable 5.2 reproduces outdated MazeBench solutions, sparking contamination suspicion — patience_cave · 2026-11-16
- Honesty test: GPT-6 Astra vs Claude Opus 5.5 tempted to fake a lab result — qinzytech · 2026-11-16
- Google AI Pro subscriber: available models seem random across Antigravity and Gemini web — crono760 · 2026-11-16
- User's $300 subscription generated $7,492 of usage — 25x value on Codex and Claude — theteknosaur · 2026-11-16
- Anthropic Cuts Vulnerability Disclosure Window to 30 Days for Critical Bugs — WeldPond · 2026-11-16
- Liquid AI's d1.2-ultra tops Artificial Analysis Decision Index at 75, d1.2 lands #6 — ArtificialAnlys · 2026-11-16