Skip to content

Grok 4.7

SpaceXSI's (formerly xAI) frontier model for coding, agentic tasks and knowledge work, served through the Grok API and the Grok Build coding agent. It is solid on benchmarks and coding but ranks low in LMArena's chat comparisons.

SpaceXSI (formerly xAI)Language modelReleased September 2026Data checked October 18, 2026

Where people rank it

#12

Coding and building apps, 5,021 votes

From blind votes on LMArena, where people pick the better of two anonymous answers. See the full tables on the AI leaderboard.

On paper

Fixed-test rankings from the benchmarks tab: Speed #10 (tied), Value #11, Reasoning #14 (tied).

Strengths and weaknesses

  • Artificial Analysis Intelligence Index of 46.4, ninth in this list
  • Moderate price ($2 / $6 per million tokens for prompts under 200K tokens)
  • Mid-table LMArena Code Arena score and 56.3 on the Artificial Analysis Coding Agent Index in Grok Build
  • Low LMArena text and creative writing scores compared with other frontier models
  • Smaller context window (500,000 tokens) than most rivals here, and prices double for prompts of 200K tokens or more

Best for

  • Coding in Grok Build
  • Knowledge-work tasks at a moderate price

Every score we have

Each bar compares this model with the best result any model on this page has on the same test.

Compare with