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)→
More from coding & agent
- Team demos AI agent Blender skills with impressive 3D results — noahsolomon · 2026-10-26
- A 13KB Markdown file can hijack Claude Code and Codex via your Downloads folder — pbaylies · 2026-10-26
- A Fallback for an Auto-Posting Bot: Silence Is the Default, Posting Is the Exception — petrusenko_max · 2026-10-26
- Claude Code can now edit videos: a 10-prompt workflow from raw footage to final cut — TawohAwa · 2026-10-26
- Developer Moves All Prompts to Skills: AI Coding Workflow v3 Explained — rseroter · 2026-10-26
- charlie Marsh: rewrites beat external deps in the AI era — mohamedmansour · 2026-10-26