Blogger: Astra-max's eyebench-v3 dominance is 'just not fair'
adonis_singh · x · 2026-09-05
A repost in the same thread reiterating that Astra-max scores 95% on eyebench-v3 at half the cost of Sol-max with 3.8x fewer output tokens and nearly double the score. No new information.
Related event: Astra-max scores 95% on eyebench-v3 at half the cost of Sol-max(3 posts)→
More from Models
- Theory: Most of Google Astra's Gains Come From Vision, Not Coding — dumquestions · 2026-09-05
- Best-Value AI Subscriptions Under $20/$200, Updated for AA Index v4.2 — popiazaza · 2026-09-05
- antirez: Astra is a big jump for software dev as RLVR-scaled models keep growing — antirez · 2026-09-05
- Heavy user: ChatGPT's Astra intuitively outclasses Claude Fable 5.1 at the same price — DynaBeast · 2026-09-05
- Fable 5.1 refuses questions on Evoscale/Biohub papers, drawing 'Opus'ed' quip — nathanbenaich · 2026-09-05
- GPT-6 Astra and Claude give opposite answers to the same simple PC check — Jardani_xx · 2026-09-05