Artificial Analysis’ Intelligence Index v5 now bases 60% of its score on evaluations with private test sets or held-out answers, with…

First reported Oct 28, 2026, 02:56 UTC

Source reports

Artificial Analysis’ Intelligence Index v5 now bases 60% of its score on evaluations with private test sets or held-out answers, with Claude Opus 5.5 narrowly leading GPT-6 Astra and GPT-6.1 Sol. As expected, GPT-6-Astra currently appears to be slightly ahead in scientific… — @kimmonismus (X), Oct 28, 2026, 02:56 UTC
Artificial Analysis launches Intelligence Index v5 with majority private datasets; Claude Opus 5.5 leads at 58 - 𝕏/@ArtificialAnlys 🔗 Discord · Leviathan · Source 🗺️ Benchmarks · Index · Claude 🕵️ @w00tcake — Rickler Feed, Oct 28, 2026, 08:24 UTC
Artificial Analysis launches Intelligence Index v5 with majority private datasets; Claude Opus 5.5 leads at 58 - 𝕏/@ArtificialAnlys 🔗 Discord · Leviathan · Source 🗺️ Benchmarks · Index · Claude 🕵️ @w00tcake — Закрепи.sender, Oct 28, 2026, 08:24 UTC

Excerpts are quoted from the linked sources, which own their text.