sonnet-5.5VIDEO
Lava lamp render test: Sonnet 5.5 and GPT 6.1 Sol pass, Kimi K3 fails
BridgeBench compared Chinese and American models on a lava lamp render test, saying Claude Sonnet 5.5 and GPT 6.1 Sol completed it easily while Kimi K3 could not render it.
Bridgebench
@bridgebenchArchived 21 days agoOriginally posted 2026.10.06
Bridgebench @bridgebenchOriginally posted 2026.10.06
China has fallen behind in the AI race. In July, Kimi K3 was supposed to be China's answer to American AI. Today it couldn't even render a lava lamp. Claude Sonnet 5.5 and GPT 6.1 Sol nailed it. Those are America's mid tier models. Right now, China can't keep up with America's second best.
x.com/bridgebench/status/2107444861607592215Archived 2026.10.07 10:29