ToolDriftRE-COUNTED EVERY NIGHT
COUNTED 09:54 UTC4 READS FAILEDRead API
Menu
COUNTED 09:54 UTC4 READS FAILED
57 models ranked12 boards36 tools tracked, 7 not what they werecaptured 29 Sep 2026against 28 Sep 202617 rose · 15 fell · 71 held · 8 newadoption, not capability
CHANGES/THE BOARD/LEADER CHANGE

Best coding model, Under $1 / M: z-ai/glm-5.2 overtook tencent/hy3

The top-ranked model for Best coding model, Under $1 / M changed from tencent/hy3 to z-ai/glm-5.2, measured on token volume through OpenRouter.

model id tencent/hy3model id z-ai/glm-5.2
OCCURRED
8 August 2026
OBSERVED
8 August 2026
SEVERITY
MEDIUM
CONFIDENCE
HIGH
LEADER CHANGEENTRY 162SOURCE auto
Contents
WHAT CHANGEDwas, and is now
WASmodel id tencent/hy3
IS NOWmodel id z-ai/glm-5.2
WHAT IT MEANSThe top-ranked model for Best coding model, Under $1 / M changed from tencent/hy3 to z-ai/glm-5.2, measured on token volume through OpenRouter.
OCCURRED8 August 2026the day the change took effect, where the vendor said so
OBSERVED2026-08-08 09:51:13 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