Elon Musk
@elonmusk
Grok Build
X Freeze@XFreeze· 10 juil. 2026Grok 4.5 with Grok Build just ranked #1 on the SWE-Atlas-QnA benchmark with a score of 84
That puts it level with GPT-5.6 (max) Codex and ahead of Claude Code Fable 5 (max), Opus 4.8 (max), and every other tested coding setup
Grok Build is now the most powerful harness for
15:47 · 10 juillet 2026 · 729,4 k vues
426
232
1,3 k