GLM-4.7 is just barely better than 4.5 Haiku on my Python instruction following benchmark in Claude Code. Not as good as 4.5 Sonnet still.
December 29, 2025 at 12:02 PM
GLM-4.7 is just barely better than 4.5 Haiku on my Python instruction following benchmark in Claude Code. Not as good as 4.5 Sonnet still.
in Claude Code, which models can read a skill file with 3 simple criteria to follow a specific code style?
Sonnet 4.5 can for sure. But haiku 4.5 cannot consistently.
Sonnet 4.5 can for sure. But haiku 4.5 cannot consistently.
December 27, 2025 at 1:18 AM
in Claude Code, which models can read a skill file with 3 simple criteria to follow a specific code style?
Sonnet 4.5 can for sure. But haiku 4.5 cannot consistently.
Sonnet 4.5 can for sure. But haiku 4.5 cannot consistently.
