Gemini 4 Carbon tops updated Artificial Analysis index as Kimi K3.1 Pro falls to ninth

Gizmodo reports Artificial Analysis says 60% of the new test involves private questions; Gemini was evaluated but not released.

2 Sources, 1d ago, first seen 1d ago

TLDR

Techmeme reported on October 28 that Artificial Analysis launched Intelligence Index v5 with new coding and science benchmarks, placing Claude Opus 5.5 (max) first at 58. Gizmodo reported on October 29 that Moonshot AI’s Kimi K3.1 Pro fell from fourth on v4 to ninth on v5, while Google’s evaluated-but-unreleased Gemini 4 Carbon topped the index at 59.

Today's Rank

—

Not ranked yet

Combined views

6.3K

2 Sources, first seen 1d ago