gpt-6IMAGE
Grok 4.7 在两项工作基准上超过 GPT-6 Astra
爆料称 Grok 4.7 在专业知识工作与多小时办公任务两项基准上均领先 GPT-6 Astra，并给出具体分数。
DogeDesigner
@cb_doge2026.09.22收录原推发布于 2026.09.22
DogeDesigner @cb_doge原推发布于 2026.09.22
BREAKING: Grok 4.7 beats GPT-6 Astra in both real-world work benchmarks: • Professional knowledge work: 1,695 vs 1,542 • Multi-hour office work: 1,657 vs 1,569 Grok 4.7 is the clear winner across both. 🔥
x.com/cb_doge/status/2102083469405000036采集于 2026.09.22 10:18