Leaked Azure entries hint at Anthropic's Claude Fable 5.5 and next-gen Opus
Screenshots from Azure's model catalog and user tests suggest Anthropic is preparing two new Claude models: Fable 5.5 and a next-generation Opus, possibly launching as soon as next week. The Fable 5.5 entry briefly appeared in Azure's catalog, and benchmark tests show a model codenamed Obsidian 3 scoring slightly above the current Opus 5.5. The leaks come amid Anthropic's upcoming IPO.
Coverage timeline
量子位量子位
Claude新模型曝光：新Fable，新Opus… Jay 2026-10-30 13:50:44 来源： 量子位 Jay 发自 凹非寺 量子位 | 公众号 QbitAI 上市在即的Anthropic，开启了连发模式。 刚刚，两款全新的Claude，被曝光了—— Fable 5.5，还有下一代Opus。 不是兄弟。 这Opus 5.5才发布多久啊，又有新模型了，还是俩？？？ 目前，这些新模型已经悄悄进入了早期测试阶段，一些网友放出的实测效果图，也是相当离谱。 A社你小子，为了IPO偷偷藏了不少好东西啊！ 所以，新模型，什么时候能出来？ 最快的话—— 下周。 Fable 5.5，要来了？ 这次的爆料，又是从X和Discord社区里传出来的。 一开始是有人发现，在Azure的模型目录里，短暂出现了一个叫claude-fable-5-5的条目，虽然很快就被删了，但截图已经满天飞了。 然后，就是各种实测截图的疯狂流出。 最经典的，自然就是咱们的鹈鹕自行车。 虽然之前模型的效果已经非常不错了，但看到Fable 5.5的输出，还是会忍不住瘫软一下、 太离谱了。 这画面质感，这光影细节，你不说，我还以为是Image 2.5生成的啊。 放大看细节，更吓人。 你敢信？？？鹈鹕嘴里甚至还叼着一条鱼。 沙滩上，有自行车轮压过的痕迹，自行车轮还有光影？？ 你搁渲染《我的世界》呢、 但不得不说，我觉得，鹈鹕自行车这道题真没啥意思了，被训练的太多。 下次换个动物吧，或者让自行车蹬鹈鹕也行。 （bushi） 除此之外，咱们经典的游戏手柄环节，也是不错的。 但这就还好了，说实话我没看出来太多门道，和之前的模型差不多。 （ps：刚发布未降智版） 不过对比下还是看得出来，Fable 5.5确实比Opus 5.5多了很多细节，这也是水桶模型的强势之处吧。 大概就是这些，消息刚出来不久，更多实测图还得继续蹲蹲、 不过，正当大家还在为Fable 5.5惊叹的时候，又来一个重磅消息。 新的Opus模型，也在路上了。 这就有点搞人了。 有开发者在基准测试平台发现了一个代号为 Obsidian 3 的模型，跑分略高于现在的Opus 5.5。 唉，AI圈现在的节奏，确实是快得有点疯狂。 前脚Google两周就发一个新模型，好不容易老头重回王座，后脚Anthropic就又准备露头就秒了。 泪目o(╥﹏╥)o。 IPO
Related stories
Leaked details: Claude and Gemini upgrades promise better reasoning, coding
According to The Information and internal testers, upcoming Claude and Gemini models show significant improvements in reasoning and coding. The new Claude reportedly identifies root causes of bugs and offers creative solutions, while Google's Gemini 4 Carbon, an upgrade to Argon, is praised by employees as comparable to Opus 5.5 on internal platforms.
1 reports · 1 sources
Anthropic unveils Claude Duet agent app in research preview
Anthropic announced Claude Duet, a proactive AI agent app for iOS, Android, and the web, built on Claude Opus 5.5. It is available as a research preview via waitlist, initially for US Pro and Max subscribers. The agent sends daily briefs and monitors connected apps, messaging users only when attention is needed.
3 reports · 3 sources
Anthropic launches Claude Haiku 5.5 with effort controls, 90% price cut
Anthropic released Claude Haiku 5.5, its cheapest and fastest small model, priced at $0.10 per million input tokens and $0.50 per million output tokens for requests up to 100K tokens, a 90% cut from Haiku 4.5. It is the first Haiku model with adjustable reasoning effort, and benchmarks show it outperforming GPT-6 Luna on several tests, including OSWorld 2.1 and GDPval-AA v2.1.
6 reports · 5 sources1045 points · 487 comments
Anthropic reportedly preparing model with superior reasoning and intent inference
The Information reports, citing a source who has tested the model, that Anthropic is preparing a new model whose reasoning and intuitive judgment exceed its current commercial models. The model is said to infer unstated user intentions, such as identifying a class of underlying bugs from a single bug-fix request and asking whether to address them all. The report also notes Google is developing a model codenamed Gemini 4 Carbon and OpenAI plans a new product possibly in the Terra series within weeks.
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe