WHAT NEW IN X11.01 SUN

AI collections from X · 22 collections · 64,204 posts

gpt-6IMAGE

Gemini 4 Argon shows 15% hallucination rate vs GPT-6 Astra's 51%

DeepLearning.AI's weekly newsletter reports that Gemini 4 Argon has a 15% hallucination rate on AA-Omniscience, far below GPT-6 Astra's 51%, though it is currently limited to Google's cybersecurity defenders.

DeepLearning.AI
@DeepLearningAIArchived 18 days agoOriginally posted 2026.10.14
Gemini 4 Argon shows 15% hallucination rate vs GPT-6 Astra's 51%
DeepLearning.AI @DeepLearningAIOriginally posted 2026.10.14
Open original on X

🎯 Gemini 4 Argon has a 15% hallucination rate on AA-Omniscience, compared with 51% for GPT-6 Astra. 📊 It ranks first on the Vals Index, reflecting its high performance in legal and other knowledge work. 🔐 For now, only cybersecurity defenders in Google's Fairwind program can use it. Full story in our weekly AI newsletter, The Batch 📬 https://hubs.la/Q04zX8YW0 #DeepLearningAI #AIEngineering #Cybersecurity

x.com/deeplearningai/status/2110037849995182297Archived 2026.10.14 11:13