Retired benchmark. These historical results are preserved for inspection and excluded from active-suite run counts. Browse the archive →
Focused model compare
Low-Poly World Explorer
Claude Fable 5.1 is the starting run, compared with GPT-6 Astra, Grok 4.7.
Starting model
Claude Fable 5.1
OpenAI
GPT-6 Astra
SpaceXAI