ToolDriftRE-COUNTED EVERY NIGHT
COUNTED 08:54 UTC4 READS FAILEDRead API
Menu
COUNTED 08:54 UTC4 READS FAILED
60 models ranked12 boards36 tools tracked, 7 not what they werecaptured 27 Sep 2026against 26 Sep 202611 rose · 12 fell · 84 held · 4 newadoption, not capability
CHANGES/THE BOARD/LEADER CHANGE

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

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

model id stepfun/step-3.7-flashmodel id z-ai/glm-5.2
OCCURRED
2 August 2026
OBSERVED
2 August 2026
SEVERITY
MEDIUM
CONFIDENCE
HIGH
LEADER CHANGEENTRY 15SOURCE auto
Contents
WHAT CHANGEDwas, and is now
WASmodel id stepfun/step-3.7-flash
IS NOWmodel id z-ai/glm-5.2
WHAT IT MEANSThe top-ranked model for Best coding model, Under $1 / M changed from stepfun/step-3.7-flash to z-ai/glm-5.2, measured on token volume through OpenRouter.
OCCURRED2 August 2026the day the change took effect, where the vendor said so
OBSERVED2026-08-02 18:57:20 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