3 karma · joined March 24, 2026
Same Three.js prompts as the rest of the field, blind human votes, ranked by quality and cost. Full set of 16 scenes is live at about $0.19 a scene (about $2.97 for the set).
Same Three.js prompts as the rest of the field, blind human votes, ranked by quality and cost. Full set of 16 scenes is live at about 1699 Elo and about $0.18, vs about $2.67 for Opus 5.5 High.
Same prompts as the rest of the field, blind human votes, ranked by quality and cost. It finished the 12 scenes at about $0.13 a scene. The other 4 scenes are still pending.
so i made a simple ab testing eval on fixed prompts: https://threejseval.com
There is a 7 degree o freedom robot arm that is really telling of the improvements in coordinates reasoning:
Luna 6 High: https://threejseval.com/models/gpt-6-luna-high
Sol 6 High: https://threejseval.com/models/gpt-6-sol-high
You can compare any other model on the same prompt. Gallery unlocks after 4 votes: https://threejseval.com
I have been building something like this with human voting, elo and ranking on multiple scenes and many models.
Here is the full interactive visualization you can play with https://nmanzini.github.io/ai-sat-mini/
It documents the Dawn-Dusk SSO mechanics, and how 100kW of orbital compute actually comes together and align to the sun and earth. I’ve integrated several videos from the visualization to show how the frame aligns in orbit for maximum power and heat dissipation.