All tasks / Tools
Grok Build
xAI's terminal coding agent with plan mode, subagents and plugins for Grok models; included in the Cursor/Grok plans.
- SpaceXAI (xAI)
- Cloud
- Free tier · from $8/mo
- Open source
Where it ranks
- BCodingCoding agents · Cloud · 56 on Artificial Analysis Coding Agent Index (v1.5)
Ranked by its own benchmark result where it has one; otherwise by the best model it offers.
Facts
- Vendor
- SpaceXAI (xAI)
- Approach
- Coding agents
- Where it runs
- Cloud only: needs the vendor’s service
- Interface
- Command line
- Skill level
- Intermediate: some setup or configuration
- Price
- Free tier · from $8/mo
- Pricing notes
- Listed as a feature of the combined Cursor/Grok plans: 'Limited' on Free, included from Plus ($8/mo) upward.
- Source code
- Open source (Apache-2.0)
- GitHub stars
- 27.5k (19 Oct 2026)
- Last verified
- 18 Oct 2026
Price from cursor.com, 18 Oct 2026.
Models it gives you
- BGrok 4.7xAI · closed
Its own benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Agent Index (v1.5) | 56 | Grok Build + Grok 4.7 (xhigh)AA label 'Grok Build - Grok 4.7 (xhigh)'; Coding Agent Index v1.5, rank 19 of 42; components (pass@1 avg of 3 attempts): DeepSWE v1.1 72.6%; SWE-Atlas-QnA 62.9%; Terminal-Bench v4 33.3%; read from the page's embedded data; no last-updated date shown | 18 Oct 2026 | artificialanalysis.ai |
| Terminal-Bench 3.0 | 26.5% | Grok Build + Grok 4.6reasoning effort: high; rank 5 of 12 entries; raw accuracy 26.49 ± 2.92 (95% CI half-width); entry date 2026-08-12; agent org: xAI; read via the site's leaderboard-read API (page is client-rendered) | 18 Oct 2026 | tbench.ai |
| Terminal-Bench 4.0 | 37.6% | Grok Build + Grok 4.7reasoning effort: xhigh; rank 21 of 35 entries; raw accuracy 37.58 ± 3.54 (95% CI half-width); entry date 2026-09-21; agent org: xAI; read via the site's leaderboard-read API (page is client-rendered) | 18 Oct 2026 | tbench.ai |