Terminal Bench 4.0得分 66.4%，超 Fable5.1 (55.8)、GPT 6 Astra (57.9%)，夸张；

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.

Opus 5 正式发布了 Terminal Bench 4.0得分 66.4%，超 Fable5.1 (55.8)、GPT 6 Astra (57.9%)，夸张； 定价也降低了：$4/$20/$0.20/$5（输入/输出/缓存读取/缓存写入） 真的有点想订 Claude 了.......这 A÷

Posted by FeiZ (8.2k followers) 1 h ago · 10 likes · 1.5k views · view the original post on X. Kept by the AI Radar as Frontier models.

More AI work like this

• use opus 5.5 on medium or high. — @Ananth7e
• is this pacing the frontier — @justalexoki
• Live look from the OpenAI office today: — @uzairansar
• What a task costs on Opus 5.5… — @cxocommunity
• Claude Opus 5.5 takes the pelican for a ride. 🚲 — @YouWareAI
• Opus 5.5 is here! — @AdamHoltererer
• Here's how Anthropic models were being used before today's Opus 5.5 launch. — @PeterJ_Walker
• roughly similar on AI R&D but a beast on agentic coding task, very impressive — @eliebakouch

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. 42.4k 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 2026-09-22 17:33 UTC. Full method.