WHAT NEW IN X11.02 MON

AI collections from X · 22 collections · 64,204 posts

Back to No.001 GPT-6 Astra in Practice: Tests, Use Cases, and FeedbackUpdated 15 hours ago
gpt-6IMAGE

MoonMapBench tests whether AI can predict elevation at 16,200 lunar coordinates

A new benchmark, MoonMapBench, asks models to predict lunar elevations; Opus 5.5 is off by 1,192 m on average and GPT-6 Astra by 1,490 m.

Ben Rank
@full__rankArchived 19 days agoOriginally posted 2026.10.13
MoonMapBench tests whether AI can predict elevation at 16,200 lunar coordinates
Ben Rank @full__rankOriginally posted 2026.10.13
Open original on X

Introducing MoonMapBench Can AI predict the elevation of 16,200 moon coordinates? Opus 5.5 on average is off by 1,192 m (3,911 ft). GPT 6 Astra is worse with 1,490 m (4,888 ft). 🧵

x.com/full__rank/status/2109677218612019601Archived 2026.10.13 10:13
Open original on X