Merge Gateway lists Grok 4.7 from xAI, citing coding gains on CursorBench and DeepSWE

shensi · x · 2026-09-22

LLM gateway service Merge announced that Grok 4.7 from xAI is now available via Merge Gateway, with coding billed as the headline improvement: 46.3% on CursorBench 4.0 versus 40.4% for Grok 4.6, and 71.0% on DeepSWE v1.1. The claim comes from a third-party gateway rather than an official xAI announcement, so details like pricing and full benchmarks remain unconfirmed.

Original post →

More from Models

Models channel →