KOL Ditches Benchmark Scores, Trusts Only Artificial Analysis Intelligence Index as Google Catches Up

XueFz · x · 2026-11-19

Developer tengyanAI admits he no longer looks at benchmark scores—because it's impossible to tell benchmaxxing apart from genuine improvement. The only metric he relies on is Artificial Analysis's Intelligence Score, which he uses to quickly gauge where a model stands relative to others and whether it's worth testing firsthand.

By that measure, he thinks Google has unexpectedly caught up with its latest model. Reposting, XueFz said it came as "no surprise at all."

The take reflects a broader fatigue in the evaluation community: static leaderboards are increasingly easy to game, and comprehensive third-party intelligence scores are becoming many people's first filter for deciding which models are worth hands-on testing.

Original post →

More from Models

Models channel →