Aditya(@adityavg13):AdityaBench findings are here! Grok 4.7 performed the worse out of all new models from these last few days Opus 5.5 thought hard before even outputting a decision GPT-6 Luna actually took more time than Sol (but costed less tokens) Unfortunately all fails! Maybe next models!

Aditya

@adityavg13

Huge Lakers fan | M.A. Global Security Studies | Currently doing stuff with AI - Token Compression and Efficiency.

加入 May 2012

921 正在关注 1.4K 粉丝

Aditya@adityavg13

2026.09.22 22:08

AdityaBench findings are here! Grok 4.7 performed the worse out of all new models from these last few days Opus 5.5 thought hard before even outputting a decision GPT-6 Luna actually took more time than Sol (but costed less tokens) Unfortunately all fails! Maybe next models!

显示更多