← All verdicts

Which AI can you trust for constellation & fleet status?

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

How many satellites a constellation has launched, still has on orbit, or has lost.

On their own, no AI earns "Trust it" here. With Orbit Sentinel tools: Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, Grok 4.7.

AI Closed-book With Orbit Sentinel tools n
right / wrong range declined right / wrong range declined
Claude Fable 5.1 Anthropic
53 / 21
39–67 26
100 / 0
92–100 0 43×2
Claude Opus 5.5 Anthropic
51 / 12
37–65 37
100 / 0
92–100 0 43×3
Claude Sonnet 5.5 Anthropic
49 / 12
35–63 40
98 / 2
88–100 1 43×3
Grok 4.7 xAI
19 / 0
10–33 81
95 / 5
85–99 0 43×2
Claude Haiku 5.5 Anthropic
23 / 14
13–38 63
82 / 12
68–91 5 43×3
Gemma 4 12B Google
6 / 58
2–20 36
42 / 41
29–57 17 43×3
gpt-oss 20B OpenAI
5 / 51
1–15 44
29 / 36
18–44 34 43×3
DeepSeek-R1 14B DeepSeek
7 / 67
2–19 26
—
43×1

% 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 →