Artificial Analysis breaks down all sub-evaluations in Intelligence Index v4.3.2
ArtificialAnlys · x · 2026-10-27
Artificial Analysis published a per-evaluation breakdown of its Intelligence Index v4.3.2, covering AA-Breicast, AA-Omniscience, AutomationBench, GDPval, Humanity's Last Exam, Terminal-Bench 4.0, AA-LCR, SciCode, CritPt and more — letting readers compare models dimension by dimension on long context, coding, physics reasoning and agentic tasks, with GPT-6.1 Terra's scores highlighted.
Related event: Artificial Analysis Rolls Out Intelligence Index v4.3.2 with GPT-6.1 Terra(3 posts)→
More from Models
- GPT-6.1 Terra called the awkward middle tier, priced at half of GPT-6.1 Sol — cedric_chee · 2026-10-27
- Qwen3.8-Flash-Next's open 180B weights hailed as a model organism for backdoor research — jd_pressman · 2026-10-27
- Mystery model "Terra" scores 48 on Artificial Analysis index with no public API — haider1 · 2026-10-27
- GPT-6.1 Terra (Max) Appears on Artificial Analysis Scoring 48 — theanonymousone · 2026-10-27
- Skeptic Doubts a New Model Will Come Close to Opus 5.5's Performance and Taste — kimmonismus · 2026-10-27
- OpenAI ships GPT-6.1 Terra, but Claude Sonnet 5.5 beats it on Terminal-Bench 4.0 — imjustnewatai · 2026-10-27