SpaceXAI / xAIProvisional

Grok Build 0.1

Grok / Grok Build 0.1 · grok-build-0.1

xAI coding model trained specifically for agentic coding workflows.

Objective score

24.4

Confidence

79%

Price evidence

Pricing evidence pending

Support this model Compare trend Official source

Other primary tiers in this family

Grok 4.3Grok Build 0.1

Scenario evidence

Six task-specific rankings

Feature development#49Obj. 24.40 · 0%Debug and repair#42Obj. 38.50 · 0%Refactoring#39Obj. 38.50 · 0%Code review#39Obj. 400 · 0%Large-repo agent work#51Obj. 20.70 · 0%Frontend / UI#38Obj. 38.50 · 0%

Evidence state

Signal coverage

Benchmarks: 2
Rank points: 8
Usage: 2
Agent: 0
Sources: 4

Objective evidence

Benchmarks and public signals

Swebench: —
Livecodebench: —
Aider: —
Artificial Analysis: 51.5
Openrouter Usage: 0
Kilo Usage: —

Persistent history

Recent ranking points

Aug 1#51 · 26

Aug 1#51 · 26

Aug 1#51 · 26

Jul 31#51 · 26

Jul 31#51 · 26

Jul 31#51 · 26

Usage signals

OpenRouter0%

Overall0%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.

Source trail

Official xAI docs say Grok Build is the dedicated code model.Artificial Analysis Coding Agents · ok WebDev Arena · ok Kilo leaderboard · ok SpaceXAI / xAI models · ok