Claude Opus 5.5 Official Specifications, Pricing & Benchmarks
Anthropic frontier coding & autonomous agent flagship with 1M context and 128K output.
📋 Claude Opus 5.5 Official API & System Card Specifications
Verified against official Anthropic developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- claude-opus-5-5
- Release Date
- 2026-09-22
- 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
- $ 4
- Cached Input / 1M
- $ 0.2 -95%
- Output / 1M Tokens
- $ 20
- Tiered Pricing Notes
- 1M context window; Prompt Cache read $0.20/1M (95% off), cache write $5/1M
🏆 Official Benchmark Results
Sourced from official System Card / Model Card & technical reports
Repository-scale code generation from natural language specs
OSWorld 2.0 is a benchmark of 108 long-horizon, real-world computer-use workflows spanning everyday and professional tasks.
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.
Humanity's Last Exam evaluated without external tools
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
💡 When Extended Thinking is enabled, Anthropic API requires temperature=1.0; control depth via budget_tokens.
📊 Claude Opus 5.5 Full Benchmark Scorecard
31 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 12 items
BenchCAD variant evaluated with access to a Python tool for programmatic CAD reasoning.
A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++.
Program Bench evaluates code-generation agents by asking them to recreate a program's behavior from only a compiled binary and documentation.
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.
DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.
BenchCAD is a benchmark for programmatic CAD reasoning built from 17,900 execution-verified CadQuery programs spanning 106 industrial part families, roughly half anchored to real ISO, DIN, EN, ASME, and IEC specification tables.
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.
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.
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.
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.
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 1.1 evaluates whether coding-agent changes are mergeable, using unit tests, maintainer-defined rubrics, and verifiers. Runs flagged for unfair internet use receive a zero score.
🤖 Agents & Tools 10 items
OSWorld 2.0 is a benchmark of 108 long-horizon, real-world computer-use workflows spanning everyday and professional tasks.
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.
Verified Toolathlon evaluation of agent tool-use capability, as reported in the MiMo-V2.6 release.
LatchBio SpatialBench Verified tests analysis of spatial transcriptomics data across externally validated problems, requiring the model to answer biological questions about the sample from analysis results.
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.
Version 2.1 of the Artificial Analysis GDPval evaluation of professional knowledge work, reported as an Elo rating.
LatchBio SingleCellBench tests analysis of single-cell RNA sequencing data across problems spanning standard workflows such as labeling cell types, finding differentially expressed genes, and correcting batch effects.
AA-Briefcase v1.1 evaluates multi-hour professional office work and reports Elo scores. Kept separate from unversioned AA-Briefcase results.
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.
The Legal Agent Benchmark (LAB) is Harvey's open-source benchmark for evaluating AI agents on complex, long-horizon legal work.
📐 Math 3 items
ArXivMath is a final-answer benchmark of research-level mathematics maintained by MathArena. Problems are extracted monthly from recent arXiv paper abstracts, then filtered through automated and manual checks to ensure they are self-contained, non-trivial, and verifiable.
Text-only Humanity's Last Exam variant evaluated with tool use enabled.
Text-only Humanity's Last Exam variant evaluated without tool use.
🧠 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.
BioMysteryBench evaluates a model's ability to reason through challenging molecular biology problems, reporting performance on a hard subset and on the subset of problems solved by human experts.
🏥 Domains 2 items
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 Opus 5.5
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Claude Opus 5.5 open-source or proprietary?
Claude Opus 5.5 (claude-opus-5-5) 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 Opus 5.5?
Claude Opus 5.5 supports 1000K input context and 128,000 max output tokens, priced at $4/1M input ($0.2/1M cached) and $20/1M output.