GPT-6 Astra scores 61 on AA Intelligence Index — no IQ gain over predecessor, price up 2.5x
MicahBerkley · x · 2026-09-04
Per Artificial Analysis data summarized by Grok, GPT-6 Astra scores 61 on the AA Intelligence Index — tied with GPT-5.6 Sol and Grok 4.6, meaning no intelligence gain over its predecessor. Claude Fable 5.1 leads at 66; Muse Spark 1.3 sits at 62. Improvements include halved hallucinations and some agentic wins, but there are regressions on GDPval and other benchmarks. Pricing is 2.5x higher.
Related event: GPT-6 Astra Reviews: Halved Hallucinations but 2.5x Price Hike(18 posts)→
More from Models
- OpenAI rolls out misalignment monitoring for Astra, admits it may miss harmful behavior — ShakeelHashim · 2026-09-04
- Databricks evals: GPT-6 Astra claims SOTA on OfficeQA Pro benchmarks, cheaper per task — downingARK · 2026-09-04
- Mathematician tests GPT-6 Astra: live Lean proof verification while writing arguments — teortaxesTex · 2026-09-04
- Tavus Launches Sparrow-2, Claiming #1 in End-of-Turn Detection and Interruption Handling — ycombinator · 2026-09-04
- ARC-AGI-3: 10x reasoning tokens cuts total cost from $48k to $26k vs medium — i_dg23 · 2026-09-04
- Researchers flag data contamination concerns in benchmark behind Astra's time-horizon score — dfrsrchtwts · 2026-09-04