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-5.3-flash overtook deepseek/deepseek-v4-flash-0731

The top-ranked model for Best coding model, Under $1 / M changed from deepseek/deepseek-v4-flash-0731 to z-ai/glm-5.3-flash, measured on token volume through OpenRouter.

model id deepseek/deepseek-v4-flash-0731model id z-ai/glm-5.3-flash
OCCURRED
9 September 2026
OBSERVED
9 September 2026
SEVERITY
MEDIUM
CONFIDENCE
HIGH
LEADER CHANGEENTRY 428SOURCE auto
Contents
WHAT CHANGEDwas, and is now
WASmodel id deepseek/deepseek-v4-flash-0731
IS NOWmodel id z-ai/glm-5.3-flash
WHAT IT MEANSThe top-ranked model for Best coding model, Under $1 / M changed from deepseek/deepseek-v4-flash-0731 to z-ai/glm-5.3-flash, measured on token volume through OpenRouter.
OCCURRED9 September 2026the day the change took effect, where the vendor said so
OBSERVED2026-09-09 09:51:16 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