ModelsSelected
Grok 4.7 Scores Below 4.6 on FrontierCode
Why we picked it
Grok 4.7's regression on engineering tasks matters for developers comparing AI coding assistants.
Grok 4.7 scored slightly below Grok 4.6 on FrontierCode 1.1, a benchmark for real-world engineering tasks. The model performed strongly on many difficult tasks but tended to over scope on others. This performance led to Grok 4.7 trailing behind its predecessor in the aggregate score.
Original · Cognition
On FrontierCode 1.1, our benchmark for real-world engineering tasks, Grok 4.7 scores slightly below Grok 4.6. While strong on many hard tasks, it tends to over scope on others, leading it to trail behind Grok 4.6 in the aggregate. Read more: devin.ai/blog/grok-4-7 💬 1 🔄 0 ❤️ 2 👀 152 📊 1 ⚡
