Pinned
Over the past several months, I’ve had the pleasure of working on the Grok Build team.
Through incredible dedication and long nights, we’ve built one of the best, most efficient model/harness combos in the world alongside a SOTA fullscreen TUI.
I would 100% check it out while
Replying to @ArtificialAnlys
As a coding agent, Grok 4.5 in Grok Build performs amongst the leading models: In our Artificial Intelligence Coding Agent Index that consists of DeepSWE, Terminal-Bench v2, and SWE-Atlas QnA, Grok 4.5 in Grok Build ranks on par with GPT-5.5 in Codex and below Fable 5 in Claude





