Claude Fable 5.2 Official Specifications, Pricing & Benchmarks
Anthropic November 2026 ultra-flagship frontier reasoning & research agent tier above Opus ($8/$40, $0.20 cached).
📋 Claude Fable 5.2 Official API & System Card Specifications
Verified against official Anthropic developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- claude-fable-5-2
- Release Date
- 2026-11-09
- Weight License
- Proprietary (Undisclosed)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 1,000,000 tokens (1000K)
- Max Output Tokens
- 128,000 tokens
- Input Modalities
- Text + Image + PDF
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Cloud API only (Proprietary)
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 8
- Cached Input / 1M
- $ 0.2 -98%
- Output / 1M Tokens
- $ 40
🏆 Official Benchmark Results
Sourced from official System Card / Model Card & technical reports
PhD-level Google-proof science reasoning questions
Full multimodal Humanity's Last Exam with tools
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems.
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
💡 Custom temperature disabled in reasoning mode; adjust reasoning effort/budget instead.
📊 Claude Fable 5.2 Full Benchmark Scorecard
28 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 10 items
A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++.
SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.
Program Bench evaluates code-generation agents by asking them to recreate a program's behavior from only a compiled binary and documentation.
Terminal-Bench-Science 0.1 is a Stanford-led community benchmark of 70 tasks drawn from scientific research workflows across the life, physical, earth, mathematical, and engineering sciences.
DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.
SWE-Bench Multimodal extends SWE-Bench to evaluate language models on software engineering tasks that involve visual inputs such as screenshots, UI mockups, and diagrams alongside code understanding.
FrontierSWE V2 evaluates agents on open-ended technical projects and reports mean@5. Kept separate from FrontierSWE V1 dominance-score results, which are not comparable.
Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems.
CursorBench 4.0 evaluates coding agents on long-horizon coding tasks from real Cursor sessions. Version 4.0 adds longer-horizon tasks; scores are not comparable with CursorBench 3.2.
FrontierCode 2.0 is Cognition's private benchmark assessing end-to-end code quality of coding-agent changes, including whether a repository maintainer would merge the agent's change.
🤖 Agents & Tools 8 items
Partial-credit computer-use score on OSWorld 2.1, as reported in the Claude Sonnet 5.5 release. Separate from OSWorld 2.0 and strict completion scores.
OfficeQA is a Databricks public benchmark that evaluates end-to-end grounded reasoning over a large corpus of historical U.S. Treasury Bulletin documents. Models must locate relevant tables across the corpus and perform precise numerical reasoning over them.
OfficeQA Pro evaluates AI models on professional knowledge-work questions and tasks drawn from real office workflows, including document analysis, spreadsheet reasoning, and information synthesis across business domains.
PhysicianBench is a public benchmark of 100 physician tasks carried out in an electronic health record (EHR), measuring agentic clinical task completion.
Version 2.1 of the Artificial Analysis GDPval evaluation of professional knowledge work, reported as an Elo rating.
AA-Briefcase v1.1 evaluates multi-hour professional office work and reports Elo scores. Kept separate from unversioned AA-Briefcase results.
Strict pass rate on OSWorld 2.1: fraction of tasks where every graded checkpoint is satisfied. Separate from the OSWorld 2.1 partial-credit score and from OSWorld 2.0.
AutomationBench is a tool-use benchmark that evaluates AI agents on automating real-world workflows, testing their ability to orchestrate tools and complete multi-step automation tasks.
📐 Math 2 items
Full multimodal Humanity's Last Exam evaluated with tool use enabled, distinct from its text-only subset.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions.
👁️ Multimodal 2 items
Chartography evaluates professional chart understanding with 100 expert-written tasks drawn from real charts across science, engineering, finance, manufacturing, supply chain, and healthcare.
Chartography visual chart recognition evaluated without tools, distinct from tool-assisted results.
🧠 Reasoning & Science 3 items
A comprehensive multilingual benchmark covering 42 languages that addresses cultural and linguistic biases in evaluation, with improved translation quality and culturally sensitive question subsets.
Multi-task Indic Language Understanding (MILU) covers 11 languages—10 Indic languages (Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, and Telugu) and English—and tests culturally grounded knowledge comprehension.
ARC-AGI-3 is the third-generation Abstraction and Reasoning Corpus benchmark, an interactive-reasoning evaluation designed to measure fluid, novel problem-solving ability that remains far from saturated for frontier models.
🏥 Domains 3 items
HealthBench Professional score before length adjustment. Distinct from the length-adjusted HealthBench Professional catalog metric.
HealthBench Professional evaluates model capability and safety for clinician use cases using real clinician-style chats and physician-authored grading rubrics.
An open-source benchmark for measuring performance and safety of large language models in healthcare, consisting of 5,000 multi-turn conversations evaluated by 262 physicians using 48,562 unique rubric criteria across health contexts and behavioral dimensions.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Claude Fable 5.2
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Claude Fable 5.2 open-source or proprietary?
Claude Fable 5.2 (claude-fable-5-2) is a proprietary commercial model by Anthropic. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of Claude Fable 5.2?
Claude Fable 5.2 supports 1000K input context and 128,000 max output tokens, priced at $8/1M input ($0.2/1M cached) and $40/1M output.