multimodal LLM
Claude Opus 5.5
Anthropic's recommended default model, stated to perform at the level of Claude Fable 5.1 on most work. Used for coding via Claude Code, GitHub Copilot and Kiro.
Levelmodel
Classmultimodal LLM
Parametersnot in the notes
Context1,000,000
Released22 Sep 2026
Opennessproprietary
Runs onnot in the notes
Statusactive
Benchmark Results
vendor-reportedmaintainer-runindependent
ARC-AGI-2knowledge and reasoning
high effort, $0.408/taskvendor-reported
93.3
050100
Score in %. Higher is better.
Arena Agenthuman preference arena
Claude Opus 5.5 (High)independent
14.33
050100
Score in %. Higher is better.
rank 1, Arena Agent overall
Arena Text leaderboardhuman preference arena
highindependent
1,507 ±8
1,2001,4001,600
Score in Elo; the axis starts at 1,200, as Elo has no zero. Higher is better.
rank 2, Arena Text overall
Arena Vision leaderboardhuman preference arena
highindependent
1,293 ±13
1,2701,2901,310
Score in Elo; the axis starts at 1,270, as Elo has no zero. Higher is better.
rank 11 of 165, Arena Vision overall, style control default, 165 models
Artificial Analysis Intelligence Index v4.3.2composite index
max; 57.62 per secondary orcarouterindependent
58
090180
Score in index. Higher is better.
rank 1 of 205, AA leaderboard, 205 current models
maxindependent
58
090180
Score in index. Higher is better.
rank 1 of 227, AA model page, 227 models
benchlm.ai frontier compositecomposite index
vendor-reported
86.4
090180
Score in index. Higher is better.
benchlm.ai frontier top 6
CursorBenchcoding
CursorBench 4.0, maxvendor-reported
57.8
050100
Score in %. Higher is better.
Epoch Capabilities Index (ECI)composite index
maintainer-run
166.82 CI 163.54 to 170.99
090180
Score in index. Higher is better.
rank 1, Epoch AI Benchmarking Hub
FrontierCode v1.1coding
vendor-reported
54.4
050100
Score in %. Higher is better.
GDPval-AA v2.1agents and tool use
vendor-reported
1,846
1,6001,7501,900
Score in Elo; the axis starts at 1,600, as Elo has no zero. Higher is better.
Humanity's Last Examknowledge and reasoning
with tools (Anthropic)vendor-reported
67.7
050100
Score in %. Higher is better.
AA-measuredindependent
61.4
050100
Score in %. Higher is better.
OSWorld 2.0agents and tool use
partialvendor-reported
81.8
050100
Score in %. Higher is better.
SWE-bench Procoding
Self-reportvendor-reported
89.9
050100
Score in %. Higher is better.
rank 1, BenchLM aggregator, top score
system cardvendor-reported
89.9
050100
Score in %. Higher is better.
Terminal-Bench 4.0agents and tool use
xhigh, with safeguards, SE about 2.6vendor-reported
66.4
050100
Score in %. Higher is better.
official boardmaintainer-run
64.8
050100
Score in %. Higher is better.
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
successor
Claude Opus 5 is the parent (successor)medium confidencenotesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- not in the notes Not disclosed
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- 1,000,000 tokens
- Input
- text, image
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- proprietary
- Licence
- Proprietary sources
- Access routes
- API, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- Vendor cloud/API only (T1). Max output 128K (300K on Batch API). API ID claude-opus-5-5; also on Amazon Bedrock, Google Cloud Vertex AI, Microsoft Foundry, Claude Platform on AWS.
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- Anthropic docs state all current models support multilingual capabilities; Bahasa Indonesia not verified
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
DeveloperAnthropicfrontier lab, USA
Anthropicfrontier lab, USAModelClaude Opus 5.5Anthropic, multimodal LLM
Claude Opus 5.5Anthropic, multimodal LLMR&D TopicsFrontier Pretraining Scaling
Use CasesIndustrial Copilots and Maintenance AssistantsIndustrialClinical LLM (Frontier Proprietary)HealthcarePharma Documents, Regulatory and Life-Science R&DHealthcareAmbient Clinical ScribingHealthcare+2 moreUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026
Banner HealthIn production, 11 Jan 2026CommureIn production, 11 Jan 2026FlatironIn production, 11 Jan 2026+39 moreDeployments of these use cases; none names this model.
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026Banner HealthIn production, 11 Jan 2026CommureIn production, 11 Jan 2026FlatironIn production, 11 Jan 2026+39 moreDeployments of these use cases; none names this model.Organisations 1
Sources
- Claude Opus 5.5 platform.claude.com https://platform.claude.com/docs/en/models/opus-5-5/overview
- Models overview platform.claude.com/docs/en/models/overview https://platform.claude.com/docs/en/models/overview
- Newsroom anthropic.com https://www.anthropic.com/news
- Claude Opus 5.5 (max with fallback) - Intelligence, Performance & Price Analysis | Artificial Analysis artificialanalysis.ai https://artificialanalysis.ai/models/claude-opus-5-5
- Claude Opus 5.5: Fable-Class Work, Cheaper to Run llm-stats.com https://llm-stats.com/blog/research/claude-opus-5-5-launch
- Models overview platform.claude.com/docs/en/about-claude/models/overview https://platform.claude.com/docs/en/about-claude/models/overview
- SWE-bench Pro Leaderboard: Claude Opus 5.5 Leads at 89.9% benchlm.ai https://www.benchlm.ai/benchmarks/swePro
- AI benchmarks & capabilities epoch.ai https://epoch.ai/benchmarks
- Arena Leaderboard: Official AI Model Rankings & Benchmarks arena.ai https://arena.ai/leaderboard
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Claude Opus 5.5", https://aurion.semai.id/models/anthropic-claude-opus-5-5/, records of October 2026.