ToolDriftRE-COUNTED EVERY NIGHT
COUNTED 08:45 UTC4 READS FAILEDRead API
Menu
COUNTED 08:45 UTC4 READS FAILED
61 models ranked12 boards36 tools tracked, 7 not what they werecaptured 26 Sep 2026against 25 Sep 202618 rose · 13 fell · 72 held · 8 newadoption, not capability
CHANGES/THE BOARD/LEADER CHANGE

Best coding model, Free: poolside/laguna-s-2.1:free overtook z-ai/glm-5.2:free

The top-ranked model for Best coding model, Free changed from z-ai/glm-5.2:free to poolside/laguna-s-2.1:free, measured on token volume through OpenRouter.

model id z-ai/glm-5.2:freemodel id poolside/laguna-s-2.1:free
OCCURRED
7 September 2026
OBSERVED
7 September 2026
SEVERITY
MEDIUM
CONFIDENCE
HIGH
LEADER CHANGEENTRY 410SOURCE auto
Contents
WHAT CHANGEDwas, and is now
WASmodel id z-ai/glm-5.2:free
IS NOWmodel id poolside/laguna-s-2.1:free
WHAT IT MEANSThe top-ranked model for Best coding model, Free changed from z-ai/glm-5.2:free to poolside/laguna-s-2.1:free, measured on token volume through OpenRouter.
OCCURRED7 September 2026the day the change took effect, where the vendor said so
OBSERVED2026-09-07 09:51:17 UTCthe night this site read it and saw a difference
EVIDENCEopenrouter.ai
HOW THIS WAS FOUNDhigh confidence

Derived from an API, a repository status or an ownership record, not a reading of a marketing page. Source: auto. Medium severity says how much it changes what the tool costs or what you get free.

EVERY BOARD, IN FULLALL CHANGES