Grok 4.5 Ties Competitor on Coding Benchmark

elonmusk · x · 2026-07-11

Grok 4.5 paired with Grok Build has tied with Codex GPT-5.6 on the SWE-Atlas-QnA benchmark, scoring 84. The repost describes this as another leap forward for xAI in coding and agentic capabilities, noting that this feature is now accessible via the new Meta Model API and Meta AI.

Related event: Grok 4.5 Tops Coding Benchmark with High Token Efficiency(3 posts)→

Original post →

More from coding & agent

coding & agent channel →