WHAT NEW IN X11.06 FRI

X 上的 AI 合集档案 · 23 个合集 · 69,408 条

gpt-6IMAGE

幻觉率横评:Gemini 4 Argon 15%,GPT-6 Astra 45%

一份模型幻觉率对比显示 Gemini 4 Argon 仅 15%,远低于 Grok 4.7 的 29%、GPT-6 Astra 的 45% 和 Opus 5.5 的 59%。

Mr Nobody
@Airo_072026.10.02收录原推发布于 2026.10.01
幻觉率横评:Gemini 4 Argon 15%,GPT-6 Astra 45%
Mr Nobody @Airo_07原推发布于 2026.10.01
在 X 上打开原推

Gemini 4 Argon might have learned AI’s most underrated skill: saying “I don’t know.” Hallucination rate: Gemini : Argon: 15% Grok 4.7: 29% GPT-6 Astra: 45% Opus 5.5: 59% Fable 5.1: 69% Argon would rather admit uncertainty than make something up. Bro is truthful AI 😂

x.com/airo_07/status/2105480328924344584采集于 2026.10.02 10:06