GPT-6 Astra priced 2.5x higher: hallucinations halved, token efficiency up 70%
ArtificialAnlys · x · 2026-09-04
Artificial Analysis' key takeaways on GPT-6 Astra:
Pricing: 2.5x increase across the board, from $4/$20 to $10/$50 per million input/output tokens; same 90% cache-read discount and 25% cache-write premium.
Coding Agent Index: Scores 67 in Codex — roughly equal to Claude Opus 5, Fable 5, and Muse Spark 1.3; Fable 5.1 leads at 70. 70% more token-efficient than GPT-5.6 Sol (about one-third the tokens, one-fifth of Claude Opus 5 xhigh). Matches Fable 5 at less than half the per-task cost, leading the cost-efficiency frontier.
Intelligence Index: Scores 61, level with GPT-5.6 Sol, 5 points behind Claude Fable 5.1 and behind Meta's Muse Spark 1.3 (max). 10% fewer output tokens, but 75% more expensive per task due to the price hike.
Hallucination & long-horizon work: Hallucination rate drops from 92% to 51% (accuracy up 4 points); 80-point gain in AA-Briefcase long-horizon evaluation.
Related event: GPT-6 Astra Reviews: Halved Hallucinations but 2.5x Price Hike(18 posts)→
More from Models
- 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
- antirez: judge new models by whether they fix real blocking bugs, not three.js demos — antirez · 2026-09-04