ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Anthropic
Proprietary API Anthropic · claude-fable-5-2 · Text+Image+PDF

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

API Model ID: claude-fable-5-2

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

Arena Elo ~1548 AA Index 62
🧠 Reasoning
GPQA Diamond 94.8 %

PhD-level Google-proof science reasoning questions

🧠 Reasoning
HLE-Full (w/ Tools) 65.2 %

Full multimodal Humanity's Last Exam with tools

💻 Coding
SWE-bench Verified 84.6 %

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.

🤖 Agentic
Terminal Bench 4.0 58.4 %

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

Official Reasoning & Tool Config
temperature=1 top_p=0.95 max_tokens=65,536

💡 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

⚔️ Compare head-to-head

💻 Coding 10 items

SWE-bench Multilingual #1/33 96.6%

A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++.

SWE-Bench Pro #1/52 93%

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 #2/18 85.6%

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 #2/16 74.6%

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 #7/49 74.3%

DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

SWE-Bench Multimodal #1/7 74.1%

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 #1/7 69.9%

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 #2/31 67.6%

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 #1/4 60%

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 #1/5 49.1%

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

OSWorld 2.1 (partial) #1/7 89.3%

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 #1/4 83.4%

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 #1/15 72.9%

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 #1/3 64.4%

PhysicianBench is a public benchmark of 100 physician tasks carried out in an electronic health record (EHR), measuring agentic clinical task completion.

GDPval-AA 2.1 #4/7 1831

Version 2.1 of the Artificial Analysis GDPval evaluation of professional knowledge work, reported as an Elo rating.

AA-Briefcase v1.1 #3/7 1785

AA-Briefcase v1.1 evaluates multi-hour professional office work and reports Elo scores. Kept separate from unversioned AA-Briefcase results.

OSWorld 2.1 (strict) #1/4 54.6%

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 #6/26 51.4%

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.

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

Compare with these →

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.