NotAnotherBench

GROUNDED IN REAL HUMAN CONVERSATIONSYOUR BENCH

PROBLEMS

Grok 4.7 problems

Complaints distilled from real conversations, 22,976 voices so far. Nothing here is invented.

ALTERNATIVES XAI MODELS

WHAT PEOPLE COMPLAIN ABOUT

Refuses or lectures more than people like (144 mentions)
Outages, errors, or limits get in the way (69 mentions)
Coding help disappoints some people (56 mentions)
People find it expensive (33 mentions)

IN THEIR OWN WORDS

“[Bug]: Grok 4.7 xhigh reasoning effort is silently downgraded to high.”
SOURCE >
“Grok 4.7 is about 2.5 times as expensive as 4.6.”
SOURCE >
“Is Grok 4.7 really 6x more expensive and 8x slower PER-TASK than GPT-6 Sol for comparable intelligence?”
SOURCE >