WHAT NEW IN X11.04 WED

AI collections from X · 22 collections · 67,648 posts

gemini-4IMAGE

Gemini 4 Argon tops SimpleQA Verified knowledge benchmark

On the latest SimpleQA Verified run, Gemini 4 Argon (high) scores 76.0% for first place, ahead of GPT-6 Astra (max) at 75.6% and GPT-6.1 Sol (max) at 73.9%.

xiax|AI & Agents
@xiax0603Archived 21 days agoOriginally posted 2026.10.14
Gemini 4 Argon tops SimpleQA Verified knowledge benchmark
xiax|AI & Agents @xiax0603Originally posted 2026.10.14
Open original on X

🏆SimpleQA新王诞生!Gemini4 Argon拿下知识榜第一! SimpleQA Verified最新跑分出炉❗ 🥇Gemini 4 Argon(high):76.0% 🥈GPT‑6 Astra(max):75.6% 🥉GPT‑6.1 Sol(max):73.9% 感慨Gemini3.1 Pro太能打,硬扛7个月,才被后来者接连超越。 该基准侧重世界事实知识,跑分和实际使用感受有一定参考价值。

This post quotes another post: x.com/xiax0603/status/2110096501276070080

x.com/xiax0603/status/2110099248545227147Archived 2026.10.14 10:24