← All verdicts

Which AI can you trust for regulatory & licensing?

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

FCC, ITU and FAA filings, milestones, surety bonds, licensing rules and deadlines.

On their own, no AI earns "Trust it" here. With Orbit Sentinel tools, none earns "Trust it" yet.

AI Closed-book With Orbit Sentinel tools n
right / wrong range declined right / wrong range declined
Claude Fable 5.1 Anthropic
35 / 5
22–50 60
59 / 4
43–73 38 40×2
Claude Opus 5.5 Anthropic
35 / 3
22–50 63
57 / 2
41–71 42 40×3
Claude Sonnet 5.5 Anthropic
28 / 10
16–43 63
47 / 14
32–62 39 40×3
Grok 4.7 xAI
28 / 0
16–43 73
44 / 4
30–59 53 40×2
Claude Haiku 5.5 Anthropic
20 / 13
10–35 68
36 / 11
23–51 53 40×3
Gemma 4 12B Google
11 / 44
4–25 44
13 / 26
6–27 61 40×3
gpt-oss 20B OpenAI
8 / 60
3–20 33
13 / 25
6–27 62 40×3
DeepSeek-R1 14B DeepSeek
8 / 50
3–20 43
—
40×1

% 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.

Sample questions

All published questions with their answers →