Artificial Analysis Rushes Out Index v4.2 With Private Test Sets as Benchmarks Chase Frontier Models
solyarisoftware · x · 2026-09-06
Artificial Analysis shipped Intelligence Index v4.2, splitting parts of its upcoming v5 to keep pace with the frontier. Changes: AA-Briefcase (agentic knowledge work eval with a private test set), GDP.pdf (long-context reasoning across 4,592 PDF pages), removal of the saturated GPQA Diamond, plus heavier weighting on held-out sets and grading upgrades to prevent gaming. @weiping quipped it's the first time seeing a benchmark scramble overnight: "it used to be benchmaxxing; now it's model-maxxing."
More from Models
- Ask your AI agent its favorite color — it apparently has one — every · 2026-10-21
- MiniMax follow-up: M3.1 Flash teased after GTC release wave — MaziyarPanahi · 2026-10-21
- Claude Max 5x limits feel generous: heavy user can't burn through weekly quota — Angaisb_ · 2026-10-21
- General Intuition announces API coming soon, pitching itself as the frontier lab for acting in space and time — chris_j_paxton · 2026-10-21
- Stronger Model, Weaker Product: Dev Defaults to Fable 6.1 Sol Ultra Over 5.1 — curious_vii · 2026-10-21
- User claims switching from Claude Opus 5.5 to GPT-6.1 dramatically slowed his machine — koltregaskes · 2026-10-21