Anthropic model product
Claude Opus 5.5
5 is a Claude model for long-running agentic coding and knowledge work.
Updated Sep 25, 2026. Default version: Claude Opus 5.5
LLMBoard Score97.9Claude Opus 5.5
Coverage40%23 benchmark families
Context window1MTokens
Official input price$4Anthropic API
Claude Opus 5.5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Opus 5.5 Benchmark Results
Benchmark scores for Claude Opus 5.5.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkArXivMath | Score91.20% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBenchCAD | Score73.00% | Rank01 | Participants5 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBenchCAD (with Python tool) | Score96.20% | Rank01 | Participants5 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkChartography | Score89.00% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkFrontierCode 1.1 | Score54.40% | Rank01 | Participants20 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGlobal-MMLU | Score94.30% | Rank01 | Participants6 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHealthBench | Score60.60% | Rank01 | Participants11 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (no tools, text-only) | Score64.40% | Rank01 | Participants8 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (with tools, text-only) | Score67.70% | Rank01 | Participants10 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld 2.0 | Score81.80% | Rank01 | Participants14 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkProgram Bench | Score91.20% | Rank01 | Participants11 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score93.90% | Rank01 | Participants46 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Multimodal | Score61.40% | Rank01 | Participants5 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score89.90% | Rank01 | Participants59 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 4.0 | Score66.40% | Rank01 | Participants19 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkAA-Briefcase v1.1 | Score1,822.00 points | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCursorBench 4.0 | Score57.80% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkFrontierSWE V2 | Score62.30% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGDPval-AA 2.1 | Score1,846.00 points | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkToolathlon-Verified | Score77.80% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLatchBio SingleCellBench | Score61.20% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLatchBio SpatialBench Verified | Score72.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMILU | Score93.10% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOfficeQA | Score78.90% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBioMysteryBench | Score89.30% | Rank02 | Participants6 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkHealthBench Professional | Score65.60% | Rank02 | Participants12 | Percentile90.91% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench-Science 0.1 | Score58.70% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkDeepSWE 1.1 | Score74.20% | Rank03 | Participants38 | Percentile94.59% | EvidenceC | Evaluated |
| BenchmarkLegal Agent Benchmark | Score8.30% | Rank03 | Participants14 | Percentile84.62% | EvidenceC | Evaluated |
| BenchmarkOfficeQA Pro | Score67.70% | Rank03 | Participants10 | Percentile77.78% | EvidenceC | Evaluated |
Claude Opus 5.5 Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Claude Opus 5.5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $4 input, $20 output per 1M
- Official provider
- Anthropic
- Lowest third-party
- From $4 input, $20 output per 1M via Azure Cognitive Services
- Tracked offerings
- 24
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAzure Cognitive Services | Provider model IDclaude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderVertex | Provider model IDclaude-opus-5-5@default | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderAnthropic | Provider model IDclaude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDanthropic/claude-opus-5.5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderAzure | Provider model IDclaude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderAmazon Bedrock | Provider model IDanthropic.claude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDanthropic/claude-opus-5.5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderVertex (Anthropic) | Provider model IDclaude-opus-5-5@default | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDanthropic/claude-opus-5.5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDanthropic/claude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDanthropic/claude-opus-5.5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderOfox | Provider model IDanthropic/claude-opus-5.5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderGitHub Copilot | Provider model IDclaude-opus-5.5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderEden AI | Provider model IDanthropic/claude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderOpenCode Zen | Provider model IDclaude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDclaude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderCrossModel | Provider model IDanthropic/claude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDanthropic/claude-opus-5.5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDclaude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderVivgrid | Provider model IDclaude-opus-5-5 | Regionglobal | Input / 1M$4 | Output / 1M$20 | Context1M | Updated |
| ProviderCortecs | Provider model IDclaude-opus-5.5 | Regionglobal | Input / 1M$4.4 | Output / 1M$22 | Context1M | Updated |
| ProviderVenice AI | Provider model IDclaude-opus-5-5 | Regionglobal | Input / 1M$4.8 | Output / 1M$24 | Context1M | Updated |
| ProviderRequesty | Provider model IDclaude-opus-5-5 | Regionglobal | Input / 1M$5 | Output / 1M$25 | Context1M | Updated |
Claude Opus 5.5 Runtime Performance
Provider-specific output speed and catalog latency for Claude Opus 5.5. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderAnthropic | Output Speed64.14 tok/s | Catalog Latency8.21 s | Max Input1M | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Opus 5.5 Specifications
Technical details for the model's default version.
- Version
- Claude Opus 5.5
- Released
- Sep 22, 2026
- Knowledge cutoff
- Jun 1, 2026
- Parameters
- N/A
- Context window
- 1M
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Opus 5.5 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionClaude Opus 5.5 | Released | LLMBoard97.92 | ParametersN/A | Context1M | Max output128K | Open weightsNo | LicenseProprietary |
Models similar to Claude Opus 5.5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Fable 5.1
Anthropic
AN
Claude Opus 5
Anthropic
AN
Claude Fable 5
Anthropic
AN
Claude Mythos
Anthropic
AN
Claude Opus 4.8
Anthropic
AN
Claude Opus 4.7
Anthropic
What is Claude Opus 5.5?
Key information about Claude Opus 5.5 and its available data.
5 is a large language model from Anthropic for long-running agentic coding and knowledge work.
Data as of 2026-09-24.
FAQ
Common questions about Claude Opus 5.5.
When was Claude Opus 5.5 released?
Claude Opus 5.5's default version was released on Sep 22, 2026.
How much does Claude Opus 5.5 cost?
Claude Opus 5.5's official API price is $4 per million input tokens and $20 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $4 input and $20 output via Azure Cognitive Services.
Who created Claude Opus 5.5?
Claude Opus 5.5 was created by Anthropic.
What is the context window for Claude Opus 5.5?
The default version has a 1M token context window.
Is Claude Opus 5.5 open weight?
No. The default version is not marked as having publicly available weights.