Visualizing how Artificial Analysis Intelligence Index weights shift across every version
HamelHusain · x · 2026-11-12
Bryan Bischof visualized how the benchmark weights behind the Artificial Analysis Intelligence Index (9 benchmarks with arbitrary weights) changed from v4 through v5: coding gains FrontierCode 2.0 and Terminal-Bench-Science at 15% each, knowledge swaps in AA-Briefcase and GDP.pdf, and HLE becomes HLE-Diamond. Hamel Husain amplified it: the index's composition drifts a lot over time.
More from Models
- rasbt coins "Benchmaxxing": making the numbers look better (best optics) — infoxiao · 2026-11-12
- Claim: Claude Opus 5.5 built a horse-riding game demo in two days (unverified) — prasenx · 2026-11-12
- OpenAI engineer opens SEV0 as leaderboard scores fail to save — iansilber · 2026-11-12
- Blogger reruns February's Gemini 3.1 Pro demo against new Gemini 4 Carbon to show 9 months of progress — Angaisb_ · 2026-11-12
- Whatever happened to OpenAI's math-solving demos from October? — iam_indecisive · 2026-11-12
- Canva says its in-house design models cost 40x less than frontier models with 100x fewer parameters — samcharrington · 2026-11-12