ToolDriftRE-COUNTED EVERY NIGHT
COUNTED 08:56 UTC4 READS FAILEDRead API
Menu
COUNTED 08:56 UTC4 READS FAILED
59 models ranked12 boards36 tools tracked, 7 not what they werecaptured 24 Sep 2026against 23 Sep 202616 rose · 10 fell · 75 held · 10 newadoption, not capability
CHANGES/THE BOARD/LEADER CHANGE

Best coding model, Under $1 / M: stepfun/step-3.7-flash overtook z-ai/glm-5.2

The top-ranked model for Best coding model, Under $1 / M changed from z-ai/glm-5.2 to stepfun/step-3.7-flash, measured on token volume through OpenRouter.

model id z-ai/glm-5.2model id stepfun/step-3.7-flash
OCCURRED
3 August 2026
OBSERVED
3 August 2026
SEVERITY
MEDIUM
CONFIDENCE
HIGH
LEADER CHANGEENTRY 127SOURCE auto
Contents
WHAT CHANGEDwas, and is now
WASmodel id z-ai/glm-5.2
IS NOWmodel id stepfun/step-3.7-flash
WHAT IT MEANSThe top-ranked model for Best coding model, Under $1 / M changed from z-ai/glm-5.2 to stepfun/step-3.7-flash, measured on token volume through OpenRouter.
OCCURRED3 August 2026the day the change took effect, where the vendor said so
OBSERVED2026-08-03 09:51:11 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