Claude Opus 5.5

Claude model for long-running agentic coding and knowledge work
- Context
- 1M
- Released
- 3w ago
- Input / 1M tokens
- $4.00
- Output / 1M tokens
- $20.00
- Cached input / 1M tokens
- $0.20
- Cache write / 1M tokens
- $5.00
Sources:models.devOpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
Other published benchmarks
| Evaluation | Reported score and source |
|---|---|
| ARC-AGI-2 | 93.3% Third-party evaluator · claude-opus-5-5_high Reasoning effort: high External evaluation via Epoch AIOriginal-source terms apply |
| ARC-AGI-2 | 70.1% Third-party evaluator · claude-opus-5-5_low Reasoning effort: low External evaluation via Epoch AIOriginal-source terms apply |
| ARC-AGI-2 | 91.7% Third-party evaluator · claude-opus-5-5_max Reasoning effort: max External evaluation via Epoch AIOriginal-source terms apply |
| ARC-AGI-2 | 87.5% Third-party evaluator · claude-opus-5-5_medium Reasoning effort: medium External evaluation via Epoch AIOriginal-source terms apply |
| ARC-AGI-2 | 92.5% Third-party evaluator · claude-opus-5-5_xhigh Reasoning effort: xhigh External evaluation via Epoch AIOriginal-source terms apply |
| FrontierMath-Tier-4-v2-Private | |
| FrontierMath-Tiers-1-3-v2-Private | |
| GPQA diamond | |
| OTIS Mock AIME 2024-2025 | |
| SimpleQA Verified |
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.
Specifications
- Developer
- Anthropic
- Model family
- Claude
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- September 22, 2026
- Model ID
anthropic/claude-opus-5.5- Openness
- Closed
- License
- —
- Input modalities
- text, image, file
- Output modalities
- text
- Modality
- text+image+file->text
- Tokenizer
- Claude
- Max output tokens
- 128K
- Knowledge cutoff
- 2026-06
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- anthropic/claude-opus-5-5
- Source family
- claude-opus
- Last updated
- 2026-09-22
- Knowledge cutoff
- 2026-06
- Model context
- 1M
- Model output limit
- 128K
- Open weights
- No
- File attachments
- Yes
- Reasoning
- Yes
- Tool calling
- Yes
- Temperature control
- No
Published benchmarks
| Benchmark | Score | Evaluation details | Evidence |
|---|---|---|---|
| Terminal-Bench | 66.4 · score | xhigh effort; production safeguards with fallback · 4.0 · 2026-09-22 | Source |
| FrontierCode | 54.4 · score | Main · max effort; production safeguards with fallback · 1.1 · 2026-09-22 | Source |
| CursorBench | 57.8 · score | max effort; production safeguards with fallback · 4.0 · 2026-09-22 | Source |
| GDPval-AA | 1846 · Elo | max effort; production safeguards with fallback · 2.1 · 2026-09-22 | Source |
| AutomationBench | 40 · pass rate | max effort; production safeguards; no fallback · 2026-09-22 | Source |
| Humanity's Last Exam | 67.7 · score | max effort; with tools; production safeguards with fallback · 2026-09-22 | Source |
| Terminal-Bench-Science | 58.7 · score | max effort; production safeguards with fallback · 0.1 · 2026-09-22 | Source |
| OSWorld | 81.8 · partial score | max effort; production safeguards with fallback · 2.0 · 2026-09-22 | Source |
| Chartography | 89 · score | max effort; with tools; production safeguards with fallback · 2026-09-22 | Source |
Complete source record (JSON)
{
"id": "anthropic/claude-opus-5-5",
"name": "Claude Opus 5.5",
"description": "Claude model for long-running agentic coding and knowledge work",
"family": "claude-opus",
"last_updated": "2026-09-22",
"knowledge": "2026-06",
"attachment": true,
"reasoning": true,
"tool_call": true,
"temperature": false,
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"benchmarks": [
{
"name": "Terminal-Bench",
"score": 66.4,
"source": "https://www.anthropic.com/claude-opus-5-5",
"metric": "score",
"variant": "xhigh effort; production safeguards with fallback",
"version": "4.0",
"date": "2026-09-22"
},
{
"name": "FrontierCode",
"score": 54.4,
"source": "https://www.anthropic.com/claude-opus-5-5",
"metric": "score",
"variant": "max effort; production safeguards with fallback",
"dataset": "Main",
"version": "1.1",
"date": "2026-09-22"
},
{
"name": "CursorBench",
"score": 57.8,
"source": "https://www.anthropic.com/claude-opus-5-5",
"metric": "score",
"variant": "max effort; production safeguards with fallback",
"version": "4.0",
"date": "2026-09-22"
},
{
"name": "GDPval-AA",
"score": 1846,
"source": "https://www.anthropic.com/claude-opus-5-5",
"metric": "Elo",
"variant": "max effort; production safeguards with fallback",
"version": "2.1",
"date": "2026-09-22"
},
{
"name": "AutomationBench",
"score": 40,
"source": "https://www.anthropic.com/claude-opus-5-5",
"metric": "pass rate",
"variant": "max effort; production safeguards; no fallback",
"date": "2026-09-22"
},
{
"name": "Humanity's Last Exam",
"score": 67.7,
"source": "https://www.anthropic.com/claude-opus-5-5",
"metric": "score",
"variant": "max effort; with tools; production safeguards with fallback",
"date": "2026-09-22"
},
{
"name": "Terminal-Bench-Science",
"score": 58.7,
"source": "https://www.anthropic.com/claude-opus-5-5",
"metric": "score",
"variant": "max effort; production safeguards with fallback",
"version": "0.1",
"date": "2026-09-22"
},
{
"name": "OSWorld",
"score": 81.8,
"source": "https://www.anthropic.com/claude-opus-5-5",
"metric": "partial score",
"variant": "max effort; production safeguards with fallback",
"version": "2.0",
"date": "2026-09-22"
},
{
"name": "Chartography",
"score": 89,
"source": "https://www.anthropic.com/claude-opus-5-5",
"metric": "score",
"variant": "max effort; with tools; production safeguards with fallback",
"date": "2026-09-22"
}
],
"release_date": "2026-09-22",
"open_weights": false
}Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| amazon-bedrock | 1M | $4.00 | $20.00 | $0.20 | $5.00 | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| amazon-bedrockBatch pricing | 1M | $4.00 | $20.00 | $0.20 | $5.00 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| anthropic | 1M | $4.00 | $20.00 | $0.20 | $5.00 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| anthropicBatch pricing | 1M | $4.00 | $20.00 | $0.20 | $5.00 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| azure/global | 1M | $4.00 | $20.00 | $0.20 | $5.00 | 95.39% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| azure/globalBatch pricing | 1M | $4.00 | $20.00 | $0.20 | $5.00 | 97.45% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| claude-on-aws | 1M | $4.00 | $20.00 | $0.20 | $5.00 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| claude-on-awsBatch pricing | 1M | $4.00 | $20.00 | $0.20 | $5.00 | 99.93% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/global | 1M | $4.00 | $20.00 | $0.20 | $5.00 | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/globalBatch pricing | 1M | $4.00 | $20.00 | $0.20 | $5.00 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| amazon-bedrock/eu-west-1 | 1M | $4.40 | $22.00 | $0.22 | $5.50 | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| amazon-bedrock/us-east-1 | 1M | $4.40 | $22.00 | $0.22 | $5.50 | 99.48% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| amazon-bedrock/eu-west-1Batch pricing | 1M | $4.40 | $22.00 | $0.22 | $5.50 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| amazon-bedrock/us-east-1Batch pricing | 1M | $4.40 | $22.00 | $0.22 | $5.50 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| azure/us | 1M | $4.40 | $22.00 | $0.22 | $5.50 | — | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| azure/usBatch pricing | 1M | $4.40 | $22.00 | $0.22 | $5.50 | — | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/us | 1M | $4.40 | $22.00 | $0.22 | $5.50 | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/europe | 1M | $4.40 | $22.00 | $0.22 | $5.50 | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/usBatch pricing | 1M | $4.40 | $22.00 | $0.22 | $5.50 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/europeBatch pricing | 1M | $4.40 | $22.00 | $0.22 | $5.50 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| anthropic/fast | 1M | $8.00 | $40.00 | $0.40 | $10.00 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| anthropic/fastBatch pricing | 1M | $8.00 | $40.00 | $0.40 | $10.00 | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Text provenance
Watermarked · GlobalClaude text watermarking
Anthropic says newer Claude models include an invisible statistical watermark globally. It changes token selection rather than adding hidden characters.
Official explanation