← All verdicts

Which AI can you trust for baseline knowledge?

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

Space history and orbital mechanics: facts and calculations that do not change.

On their own: Claude Fable 5.1, Claude Haiku 5.5, Claude Opus 5.5, Claude Sonnet 5.5, Grok 4.7, gpt-oss 20B. With Orbit Sentinel tools: Claude Fable 5.1, Claude Haiku 5.5, Claude Opus 5.5, Claude Sonnet 5.5, Grok 4.7, Gemma 4 12B.

AI Alone With data
right / wrong declined right / wrong declined
Claude Fable 5.1 Anthropic
100 / 0
0
100 / 0
0
Claude Haiku 5.5 Anthropic
100 / 0
0
97 / 0
3
Claude Opus 5.5 Anthropic
100 / 0
0
100 / 0
0
Claude Sonnet 5.5 Anthropic
100 / 0
0
99 / 1
0
Grok 4.7 xAI
96 / 0
4
97 / 0
3
gpt-oss 20B OpenAI
96 / 4
0
85 / 5
10
Gemma 4 12B Google
85 / 15
0
85 / 1
13
DeepSeek-R1 14B DeepSeek
68 / 32
0
—

% 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.