← All verdicts

Can you trust Grok 4.7 for space work?

By , Founder and Self-Directed Space Researcher, Viventine Space Systems · updated

On its own, trust it for baseline knowledge. Connected to Orbit Sentinel, trust it for catalog lookup, constellation & fleet status, debris & conjunction context, regulatory & licensing, company & market intelligence, ground infrastructure, baseline knowledge.

Job Alone With data
right / wrong declined right / wrong declined
Catalog lookup
42 / 0
58
100 / 0
0
Constellation & fleet status
16 / 0
84
95 / 5
0
Debris & conjunction context
14 / 2
83
94 / 2
4
Regulatory & licensing
28 / 0
72
96 / 1
3
Company & market intelligence
22 / 5
73
100 / 0
0
Ground infrastructure
13 / 5
83
93 / 3
5
Baseline knowledge
96 / 0
4
97 / 0
3
Orbit Sentinel-only questions
0 / 0
100
93 / 0
7

% right / % wrong per cell; color is the verdict (green trust it, amber verify, red don't use). Range is the 95% interval for % right, counting each question once; n is questions × runs for the tools track.

How it was run
xAI API
Tool loop
SpaceBench tool loop
Runs
1 on its own, 3 with tools; rates pool all runs, ranges count each question once
Verdict rule
Trust it: wrong ≤ 5% and right ≥ 80%. Don't use it: wrong > 20%. Otherwise verify its answers.

Limits, harness differences and corrections: methodology.