Opus 5.5 在 AA 智能指数拿到 58 分，超过 Fable 5.1 和 GPT-6 Astra 的 53 分，成本还降到了 Fable 5.1 的约 40%。
This is a AI post classified by Jev as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.
这就是差距！没有对比就没有伤害！ Opus 5.5 在 AA 智能指数拿到 58 分，超过 Fable 5.1 和 GPT-6 Astra 的 53 分，成本还降到了 Fable 5.1 的约 40%。 一小时后，OpenAI 发布 GPT-6 Sol 和 Luna，价格都是各自 5.6 前代的一半，但这张榜上分别只有 48 分和 37 分，连 Opus 5 的 51 分都没追上。 都在降价，Anthropic 还把能力上限往上推了一截。
Posted by KC (5.4k followers) 1 h ago · 18 likes · 3.7k views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- This chart is just models spending more money to lose to opus 5.5 on medium... — @plotarmordev
- Opus 5.5 is a first RSI model — @HarshithLucky3
- Grok 4.7 drops: lead on legal + electrical engineering, coding in the frontier pack 🤖 — @dogeofficialceo
- The boy drew a train. Claude Opus 5.5 drew the boy, in JavaScript, with Higgsfield. — @higgsfield_ai
- Claude Opus 5.5 made a phonk groove from scratch in Logic Pro with Higgsfield. — @higgsfield_ai
- GPT 6 Sol 出了！最大的特点还是降本，输出从 20 刀百万 Token 降低到了 10 刀百万 Token。 — @AstroHanRay
- So now the time for the next GPT model... 🤔 — @rohanpaul_ai
- heres the cheapest best models right now — @nicdunz
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 43.7k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 02:25 UTC. Full method.