--- title: Claude Fable 5.2 Scores 65 on Artificial Analysis,... description: Claude Fable 5.2 (Max, Default Fallback) scores 65 on the Artificial Analysis Intelligence Index, well above the median of 40 for comparable models. It costs... canonical: https://daily.dev/posts/claude-fable-5-2-scores-65-on-artificial-analysis-highest-so-far-ggb6fcsbw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Claude Fable 5.2 Scores 65 on Artificial Analysis, Highest So Far | daily.dev og:description: Claude Fable 5.2 (Max, Default Fallback) scores 65 on the Artificial Analysis Intelligence Index, well above the median of 40 for comparable models. It costs... og:url: https://daily.dev/posts/claude-fable-5-2-scores-65-on-artificial-analysis-highest-so-far-ggb6fcsbw og:image: https://api.daily.dev/og/posts/ggB6fcSBW.png og:image:alt: Claude Fable 5.2 Scores 65 on Artificial Analysis, Highest So Far og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Claude Fable 5.2 Scores 65 on Artificial Analysis, Highest So Far **[Hacker News](https://daily.dev/sources/hn)** · 5 min read · 0 upvotes · 0 comments ## Summary Claude Fable 5.2 (Max, Default Fallback) scores 65 on the Artificial Analysis Intelligence Index, well above the median of 40 for comparable models. It costs $8.00 per 1M input tokens and $40.00 per 1M output tokens, both above the $2.00 and $10.00 medians. It averages $26.54 per Intelligence Index task and takes 45.0 minutes per task versus a 12.9 minute median. Time to first answer token is 171.16 seconds, and it generated 275M tokens during evaluation versus a 72.8M median. It supports text and image input with a 1M token context window. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How much does Claude Fable 5.2 (Max) cost per 1M input and output tokens? Claude Fable 5.2 (Max, Default Fallback) costs $8.00 per 1M input tokens and $40.00 per 1M output tokens via Anthropic's API, both well above the median of $2.00 and $10.00 for comparable models. For a blended rate using a 7:2:1 cache hit/input/output ratio, the cost works out to $5.74 per 1M tokens. _Comparing LLM pricing before committing to an API gets easier with model benchmarks tracked on daily.dev._ ### How fast is Claude Fable 5.2 (Max) compared to other models at the same price point? It is notably slow, taking 45.0 minutes per Intelligence Index task compared to a median of 12.9 minutes among comparable models. Its time to first answer token is 171.16 seconds, versus a median of 13.07 seconds, and it is also very verbose, generating 275M output tokens during evaluation versus a 72.8M median. _Developers weighing latency against intelligence scores can follow model performance comparisons on daily.dev._ ### What is the Artificial Analysis Intelligence Index score for Claude Fable 5.2 (Max)? Claude Fable 5.2 (Max, Default Fallback) scores 65 on the Artificial Analysis Intelligence Index, well above the median of 40 for comparable models. It is a reasoning model with a 1M token context window, supports text and image input, and outputs text only, released November 9, 2026 by Anthropic. _Tracking intelligence index scores helps when choosing a reasoning model, something daily.dev readers follow closely._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 117 comments across hackernews (as of 2026-11-09). **TL;DR:** Discussion centers heavily on cost: at default 'max' settings Fable 5.2 is seen as drastically more expensive and token-hungry than its predecessor and rivals, though many note that at medium/high settings it's actually quite cost-competitive and sits near the efficiency frontier. **Sentiment:** 20% positive · 45% mixed · 35% skeptical **The case for** - At medium/high effort settings, it's considered highly cost-competitive and near the pareto frontier of cost vs. intelligence. - Some find it beats Opus 5.5 at lower cost, representing real progress for certain difficult/agentic tasks. - A few report it performing well on specific benchmarks or tasks like code review. **The pushback** - Running at default 'max' effort massively inflates token usage and cost per task compared to Fable 5.1. - Several argue the benchmark gains reflect diminishing returns and heavier reasoning/token spend rather than genuine efficiency gains. - Some report it ignoring explicit instructions (e.g., CLAUDE.md) or feeling arrogant/overconfident compared to prior models. - Concerns that refusals or 'moralizing' still consume quota, frustrating users. - Comparisons to cheaper models like DeepSeek or GLM suggest most use cases don't need such an expensive frontier model. **By community** - hackernews (heated): Heavy debate over whether the cost explosion is a real problem or just a matter of not using 'max' settings, alongside tangents on diminishing returns, competitor models, and refusal behavior. **Hottest debate:** Whether the dramatic cost-per-task increase represents a genuine step backward (diminishing returns) or is simply a non-issue since most users should use medium/high settings instead of max. **Open questions** - Where exactly is the line between users who truly need frontier-level models versus those over-provisioning for simple tasks? - Will training costs/efficiency improve, or are labs just scaling inference compute to chase benchmark scores? - How will usage-based billing versus plan caps evolve for heavy API users and larger enterprises? **Highlights** > Forget about the scores... look at the Cost Per Task. Fable 5.1 was already the most expensive by a good margin, and now Fable 5.2 doubles it! This is with the price cut. The output tokens per task just exploded. From 118k tokens (46k Answer/71k Reasoning) in 5.1 to 274k tokens (81k Answer/192k Reasoning) in 5.2. > — [rgbrenner on hackernews · 15 comments](https://news.ycombinator.com/item?id=50432202) > The Artificial Analysis charts are great, but be warned that they show max effort by default. Max effort is nice for revealing the limits of a model, but it's almost never used in practice. If you scroll down to the coding charts you can start adding Fable 5.2, Opus 5.5, and others at more normal difficulty settings. Fable 5.2 on medium looks quite attractive compared to Opus 5.5 high/xhigh Fable 5.2 on max (the default) looks like a good way to light your money on fire. > — [Aurornis on hackernews](https://news.ycombinator.com/item?id=50432902) > Yes, but that's running at max. Nobody is going to do that unless they want the best possible performance at all cost, in which case, they get what they asked for. Fable 5.2 at high scores a 62, which is better than anything else on the market (except Fable 5.2 at xhigh and max) -- and is about a third of the price per task. > — [jonas21 on hackernews · 1 comments](https://news.ycombinator.com/item?id=50433272) > Fable, for me (it might be a completely different experience for you) has been like the well read snobbish kid at school that openly ignores me when I ask certain questions and often asks me to talk to someone else on other questions. That kid might indeed be a genius, clearly bright, but is more interested in deciding whether I should have asked a question than in answering it. For me personally, if the best model on the planet refuses to answer why I shouldn't mix bleach and ammonia, where I'm trying to understand the chemistry behind the warning, it's not pareto frontier to one that atleast tries to and points me in a general direction. Being told that the topic is concerning, referred to someone else and charged part of my quota for that experience feels like getting an invoice from that school genius for telling me to "just ask the chemistry teacher". If my LLM asks me to rethink my life when I ask it to reverse engineer the firmware of my Samsung TV that I suspect is setting up adhoc radio networks to relay my data to Samsung's cloud, I feel rather sad, specially when that kid sends me an invoice for saying "no" At least Anthropic should not bill me for the refusal (as of my last tests, refusals still comes out of my quota) - getting slapped and pickpocketed for asking a question is really upsetting. > — [ProblemExplorer on hackernews · 3 comments](https://news.ycombinator.com/item?id=50432507) > The model feels bench maxed to me. It is back to Opus and prior Fable behavior of me pointing out constant mistakes, with it apologizing and saying that it should have looked at what I point it to. The thing is, all of these pointers are in the CLAUDE.md file, so it just ignored instructions because it thought it was smarter than the world and didn't need them. It feels really arrogant is how I would describe it. > — [nathanyz on hackernews](https://news.ycombinator.com/item?id=50433375) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=50431144) · 178 points · 117 comments ## Similar posts on daily.dev - [Is Claude Fable 5.1 Actually Cheaper Than Fable 5? I Ran the Numbers Myself](https://daily.dev/posts/is-claude-fable-5-1-actually-cheaper-than-fable-5-i-ran-the-numbers-myself-mmsrbb6gd) · Medium · 0 upvotes · 0 comments - [Anthropic’s Opus 5 is almost Fable 5](https://daily.dev/posts/anthropic-s-opus-5-is-almost-fable-5-vlen80a1c) · The New Stack · 9 upvotes · 1 comments - [$100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol](https://daily.dev/posts/100-ai-music-video-claude-fable-5-vs-gpt-5-6-sol-yzb9rxhec) · Hacker News · 4 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#llm](https://daily.dev/tags/llm), [#claude](https://daily.dev/tags/claude), [#anthropic](https://daily.dev/tags/anthropic) [View this post on daily.dev](https://daily.dev/posts/claude-fable-5-2-scores-65-on-artificial-analysis-highest-so-far-ggb6fcsbw) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Claude Fable 5.2 Scores 65 on Artificial Analysis, Highest So Far","url":"https://daily.dev/posts/claude-fable-5-2-scores-65-on-artificial-analysis-highest-so-far-ggb6fcsbw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/claude-fable-5-2-scores-65-on-artificial-analysis-highest-so-far-ggb6fcsbw"},"datePublished":"2026-11-09T21:46:35.739Z","dateModified":"2026-11-09T23:09:52.849Z","description":"Claude Fable 5.2 (Max, Default Fallback) scores 65 on the Artificial Analysis Intelligence Index, well above the median of 40 for comparable models. It costs...","image":"https://media.daily.dev/image/upload/s--58gMhC4P--/f_auto/v1722860399/public/Placeholder%2012","thumbnailUrl":"https://media.daily.dev/image/upload/s--58gMhC4P--/f_auto/v1722860399/public/Placeholder%2012","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/claude-fable-5-2-scores-65-on-artificial-analysis-highest-so-far-ggb6fcsbw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,llm,claude,anthropic","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Claude Fable 5.2 Scores 65 on Artificial Analysis, Highest So Far"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/claude-fable-5-2-scores-65-on-artificial-analysis-highest-so-far-ggb6fcsbw#faq","mainEntity":[{"@type":"Question","name":"How much does Claude Fable 5.2 (Max) cost per 1M input and output tokens?","acceptedAnswer":{"@type":"Answer","text":"Claude Fable 5.2 (Max, Default Fallback) costs $8.00 per 1M input tokens and $40.00 per 1M output tokens via Anthropic's API, both well above the median of $2.00 and $10.00 for comparable models. For a blended rate using a 7:2:1 cache hit/input/output ratio, the cost works out to $5.74 per 1M tokens. Comparing LLM pricing before committing to an API gets easier with model benchmarks tracked on daily.dev."}},{"@type":"Question","name":"How fast is Claude Fable 5.2 (Max) compared to other models at the same price point?","acceptedAnswer":{"@type":"Answer","text":"It is notably slow, taking 45.0 minutes per Intelligence Index task compared to a median of 12.9 minutes among comparable models. Its time to first answer token is 171.16 seconds, versus a median of 13.07 seconds, and it is also very verbose, generating 275M output tokens during evaluation versus a 72.8M median. Developers weighing latency against intelligence scores can follow model performance comparisons on daily.dev."}},{"@type":"Question","name":"What is the Artificial Analysis Intelligence Index score for Claude Fable 5.2 (Max)?","acceptedAnswer":{"@type":"Answer","text":"Claude Fable 5.2 (Max, Default Fallback) scores 65 on the Artificial Analysis Intelligence Index, well above the median of 40 for comparable models. It is a reasoning model with a 1M token context window, supports text and image input, and outputs text only, released November 9, 2026 by Anthropic. Tracking intelligence index scores helps when choosing a reasoning model, something daily.dev readers follow closely."}}]} ```