# Claude Opus 5.5

Anthropic · Proprietary · rank 1 · bench-align-v5

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/models/claude-opus-5-5  
JSON: https://modelscale.dev/api/model/claude-opus-5-5

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `claude-opus-5-5` | — |
| Overall score | 86.68 | Observed 2026-10-23 · source benchlm:models |
| Context window | 1M tokens | Observed 2026-10-23 · source benchlm:models |
| Release date | 2026-09-22 | Observed 2026-10-23 · source benchlm:models |
| Access type | Proprietary | — |
| Blended $/1M (75% input / 25% output) | $8.00 | Derived from the input and output rates below |

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero.

| Axis | Score | Evidence |
| --- | --- | --- |
| Agentic | 65.3 | Observed 2026-10-23 · source benchlm:models |
| Coding | 87.5 | Observed 2026-10-23 · source benchlm:models |
| Knowledge | 85.4 | Observed 2026-10-23 · source benchlm:models |
| Reasoning | 86.1 | Observed 2026-10-23 · source benchlm:models |
| Multimodal & Grounded | 92.2 | Observed 2026-10-23 · source benchlm:models |
| Instruction Following | Unavailable | Unavailable · source benchlm:models |
| Math | 97.3 | Observed 2026-10-23 · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | 573.15 s | 2026-10-23 | 2026-10-23 | Observed 2026-10-23 · source benchlm:speed |
| Throughput | 95 tok/s | 2026-10-23 | 2026-10-23 | Observed 2026-10-23 · source benchlm:speed |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | $4.00 | Observed 2026-10-23 · source benchlm:pricing |
| Output / 1M tokens | $20.00 | Observed 2026-10-23 · source benchlm:pricing |
| Cache read / 1M tokens | $0.20 | Observed 2026-10-23 · source benchlm:pricing |
| Cache write / 1M tokens | $5.00 | Observed 2026-10-23 · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $8.00 | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Fetch failed · source livebench:table |

**Self-hosted listing.** Anthropic's September 22, 2026 Claude Opus 5.5 model documentation lists the `claude-opus-5-5` API model at $4 input / $20 output per million tokens, with $0.20 cache reads. Five-minute and one-hour cache writes are $5 and $8 per million tokens; Batch API input and output receive a 50% discount. The rates above are a hosted price matched from another provider, not a first-party list price.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | $22.53 |
| Modelled tokens | 2.82M |

## Benchmark record

83 matched benchmark rows with their published value, unit, and provenance.

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| HealthBench (raw) (HealthBench raw score) | 68.1 | 5,000 multi-turn patient conversations | Realistic healthcare conversations | [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://arxiv.org/abs/2505.08775) |
| HealthBench (length-adjusted) (HealthBench length-adjusted score) | 60.6 | 5,000 multi-turn patient conversations | Realistic healthcare conversations | [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://arxiv.org/abs/2505.08775) |
| HealthBench Professional (raw) (HealthBench Professional raw score) | 77.1 | 525 physician-authored conversations | Professional clinical tasks | [HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats](https://arxiv.org/abs/2604.27470) |
| BioMysteryBench (human-solvable) (BioMysteryBench Human Solvable) | 89.3 | Human-solvable computational biology investigations | Expert computational biology | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| BioMysteryBench (human-difficult) (BioMysteryBench Human Difficult) | 50.0 | Human-difficult computational biology investigations | Frontier computational biology | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| SpatialBench Verified (LatchBio SpatialBench Verified) | 72.0 | 115 externally validated spatial transcriptomics problems | Professional bioinformatics | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| SingleCellBench (LatchBio SingleCellBench) | 61.2 | 195 single-cell RNA sequencing problems | Professional bioinformatics | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Protein Design (Anthropic Protein Design evaluation) | 60.2 | Constrained protein-sequence design tasks | Computational protein design | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Protocols (troubleshooting) (Molecular Biology Protocols Troubleshooting) | 73.7 | Molecular-biology protocol troubleshooting | Expert laboratory protocols | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Protocols (understanding) (Benchling Molecular Biology Protocols Understanding) | 69.0 | Molecular-biology protocol extension | Expert laboratory protocols | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| HLE (Humanity's Last Exam) | 67.7 | Expert-level questions | Frontier expert level | [Humanity's Last Exam](https://lastexam.ai/) |
| Artificial Analysis Intelligence Index | 57.6 | Cross-benchmark intelligence index | Display-only external reference | [Artificial Analysis](https://artificialanalysis.ai/) |
| AA-HLE (Artificial Analysis Humanity's Last Exam) | 61.4 | Expert-level questions | Frontier expert reasoning | [Artificial Analysis Humanity's Last Exam Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/hle) |
| AA-Omniscience Index (Artificial Analysis Omniscience Index) | 46.4 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 66.2 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA-Omniscience Hallucination Rate (Artificial Analysis Omniscience Hallucination Rate) | 58.6 | Knowledge questions | Factuality | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| HealthBench Professional | 65.6 | Clinician chat tasks | Professional clinical workflows | [HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats](https://arxiv.org/abs/2604.27470) |
| HLE w/o tools (Humanity's Last Exam without tools) | 64.4 | Expert-level questions | Frontier expert level | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| Morphology-to-molecule matching (Axiom Bio morphology-to-molecule matching) | 34.0 | Four multi-channel cell-imaging perturbation-matching tasks | Biomedical image and molecular reasoning | [Claude Opus 5.5 System Card](https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf) |
| Medicinal chemistry (Anthropic medicinal-chemistry evaluation) | 63.5 | 504 molecular-property questions | Medicinal chemistry reasoning | [Claude Opus 5.5 System Card](https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf) |
| Protein Design library ranking (Anthropic protein-design library-ranking task) | 56.0 | 83 protein-design library-ranking problems | Computational protein design | [Claude Opus 5.5 System Card](https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf) |
| De novo protein-binder design (Anthropic de novo protein-binder design evaluation) | 82.6 | 15 protein targets | Long-horizon computational protein design | [Claude Opus 5.5 System Card](https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| SWE-bench Pro | 89.9 | 1,865 repository problems | Long-horizon professional engineering | [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://arxiv.org/abs/2509.16941) |
| FrontierCode 1.1 Main | 54.4 | 100 private Main tasks (150 in Extended) | Frontier coding-agent quality | [FrontierCode leaderboard](https://cognition.com/frontiercode) |
| FrontierCode 1.1 Extended | 63.6 | 150 private software-engineering tasks | Frontier coding-agent quality | [FrontierCode leaderboard](https://cognition.com/frontiercode) |
| SWE Multilingual | 93.9 | Multilingual software-engineering tasks | Professional software engineering | [MiniMax M2.7: Early Echoes of Self-Evolution](https://www.minimax.io/news/minimax-m27-en) |
| SWE Multimodal (SWE-bench Multimodal) | 61.4 | Multimodal software engineering tasks | Frontier multimodal coding | [SWE-bench Multimodal](https://www.swebench.com/multimodal) |
| ProgramBench (ProgramBench: Can Language Models Rebuild Programs From Scratch?) | 91.2 | 200 program reconstruction tasks | Full-repository software architecture | [ProgramBench: Can Language Models Rebuild Programs From Scratch?](https://programbench.com/static/paper.pdf) |
| FrontierSWE v2 | 62.3 | 34 ultra-long-horizon engineering and research tasks | Ultra-long-horizon frontier software engineering | [FrontierSWE v2](https://www.frontierswe.com/blog/v2) |
| Bug Hunt Bench | 41.7 | 105 planted bugs across two production TypeScript repositories | Blind production-repository bug finding and repair | [Bug Hunt Bench method, caveats, and definitions](https://bughunt.productcompass.pm/method) |
| AA-SciCode (Artificial Analysis SciCode) | 66.9 | Scientific coding subproblems | Scientific programming | [Artificial Analysis SciCode Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/scicode) |
| DeepSWE | 74.2 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | [DeepSWE benchmark blog](https://deepswe.datacurve.ai/blog) |
| PostTrainBench v1.1 | 49.3 | Post-training Qwen3 1.7B and 4B, SmolLM3 3B, and Gemma3 4B | Frontier agent evaluation | [PostTrainBench v1.1 leaderboard and methodology](https://posttrainbench.com/?version=v1.1) |

### Mathematics

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| FrontierMath v2 (Tiers 1-3) (FrontierMath v2 Tiers 1-3) | 91.228 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | [FrontierMath v2 benchmark hub](https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2) |
| FrontierMath v2 (Tier 4) (FrontierMath v2 Tier 4) | 95.000 | 41 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | [FrontierMath Tier 4 v2 leaderboard](https://epoch.ai/benchmarks/frontiermath-tier-4-v2?view=graph&tab=leaderboard) |
| ArXivMath Aug. 2026 (no tools) (ArXivMath August 2026 without tools) | 91.2 | 57 recent research-mathematics problems | Research mathematics | [Claude Opus 5.5 System Card](https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf) |
| ArXivMath Aug. 2026 (tools) (ArXivMath August 2026 with tools) | 96.9 | 57 recent research-mathematics problems | Research mathematics | [Claude Opus 5.5 System Card](https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| ARC-AGI-1 (ARC-AGI-1 Semi-Private Evaluation) | 97.50 | Semi-private ARC-AGI-1 evaluation set | Abstract visual reasoning | [ARC Prize leaderboard](https://arcprize.org/) |
| ARC-AGI-2 (Abstraction and Reasoning Corpus for AGI v2) | 91.666667 | Visual pattern completion and abstract reasoning | Expert-level — hardest public reasoning benchmark | [ARC-AGI-2: A Harder General Intelligence Benchmark](https://arcprize.org/arc-agi/2/) |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 84.7 | Long-context reasoning tasks | Long-context reasoning | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| MLCR-AA (Medical Long Context Reasoning (MLCR-AA)) | 66.7 | Long, fragmented medical-record reasoning | Long-context medical reasoning | [Medical Long Context Reasoning (MLCR-AA)](https://artificialanalysis.ai/evaluations/mlcr-aa) |
| CritPt (Critical Physics Tasks) | 31.7 | Research-level physics questions | Research-level physics reasoning | [CritPt Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/critpt) |
| GraphWalks BFS 256K–1M | 66.8 | Breadth-first-search graph traversal on 200 problems with context lengths from 256K to 1M tokens. | Frontier agent evaluation | [Gemini 4 Argon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-argon) |
| STEMBench (STEMBench120: six-domain scientific research progress) | 2.62 | 120 research tasks, 20 in each of six STEM domains | Open research targets; no run has reached a full-target success | [STEMBench: six-domain model evaluation](https://www.ulam.ai/stembench) |

### Multilingual

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GMMLU (Global MMLU) | 94.3 | Knowledge questions across 42 languages | Multilingual knowledge | [Global MMLU: Understanding and addressing cultural and linguistic biases in multilingual evaluation](https://arxiv.org/abs/2412.03304) |
| MILU (Multi-task Indic Language Understanding Benchmark) | 93.1 | Knowledge tasks across 11 languages | Multilingual Indic knowledge | [MILU: A Multi-task Indic language understanding benchmark](https://arxiv.org/abs/2411.02538) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| LAB all-pass (Harvey held-out) (Legal Agent Benchmark all-pass rate — Harvey held-out set) | 8.3 | Harvey-held-out legal-agent tasks | Professional legal work | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| LAB criterion-pass (Harvey held-out) (Legal Agent Benchmark mean criterion-pass rate — Harvey held-out set) | 91.2 | Harvey-held-out legal-agent tasks | Professional legal work | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Toolathlon Verified Pass@3 | 82.4 | 108 verified real-world tool-use tasks | Long-horizon application tool use | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Toolathlon Verified Pass³ (Toolathlon Verified Pass cubed) | 72.2 | 108 verified real-world tool-use tasks | Long-horizon application tool use | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Toolathlon Verified avg. turns (Toolathlon Verified average assistant turns) | 26.9 | 108 verified real-world tool-use tasks | Long-horizon application tool use | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| Terminal-Bench 4.0 | 66.40 | 66 professional computer-work tasks | Frontier autonomous knowledge work | [Terminal-Bench 4.0](https://www.tbench.ai/news/terminal-bench-4-0) |
| Terminal-Bench-Science 0.1 | 58.7 | 70 expert-curated scientific research workflows | Frontier scientific research workflows | [Terminal-Bench-Science 0.1](https://www.terminal-bench-science.ai/) |
| AA Briefcase (Artificial Analysis Briefcase) | 1803 | Professional knowledge-work tasks | Professional work | [Artificial Analysis Briefcase Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-briefcase) |
| AA AutomationBench (Artificial Analysis AutomationBench) | 69.5 | Business-process automation tasks | Agentic automation | [Artificial Analysis AutomationBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/automationbench-aa) |
| AA Harvey LAB v1.0 (Artificial Analysis Harvey LAB-AA v1.0) | 91.2 | Legal agent tasks | Professional legal work | [Artificial Analysis Harvey LAB-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/harvey-lab-aa) |
| AA ITBench (Artificial Analysis ITBench-AA) | 38.2 | IT incident-response tasks | Enterprise IT operations | [Artificial Analysis ITBench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/itbench-aa) |
| HLE w/ tools (Humanity's Last Exam with tools) | 67.7 | Expert questions with tool use | Frontier tool-augmented reasoning | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA | 1846 | Agentic real-world work tasks | Professional agentic workflows | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA (GDPval-AA normalized) | 68.3 | Economically valuable tasks | Professional agentic workflows | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA Terminal-Bench 4.0 (Artificial Analysis Terminal-Bench v4.0) | 59.6 | Terminal-based agent tasks | Agentic software engineering | [Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/terminalbench-v4-0) |
| GDP.pdf (Artificial Analysis GDP.pdf) | 26.2 | Professional document-production tasks | Professional knowledge work | [GDP.pdf Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gdp-pdf) |
| AA-AnalystAgent (Artificial Analysis AnalystAgent) | 56.3 | Spreadsheet and document analysis questions | Business and data analysis | [AA-AnalystAgent Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-analyst-agent) |
| OSWorld 2.0 | 48.7 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | [OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks](https://arxiv.org/abs/2606.29537) |
| Toolathlon-Verified | 77.8 | Verified multi-tool workflows | Advanced tool use | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| AutomationBench | 40.0 | 600 public automation tasks | Long-horizon automation | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |
| CWE-bench v1 | 67.0 | Audit and patch held-out C/C++, Go, Java, TypeScript/JavaScript, Python, and Rust repositories | Frontier agent evaluation | [CWE-bench v1 leaderboard and methodology](https://cwe-bench.com/) |
| Hermes Index (Hermes Index: agentic capability and cost per task inside Hermes Agent) | 63.3 | Four suites: Hermes Bench (150 tasks), TerminalBench 4 without its 4 GPU tasks, TerminalBench Science and SkillsBench | Frontier agentic | [Hermes Index: an agentic model leaderboard](https://portal.nousresearch.com/bench) |
| Hermes Bench (Hermes Bench: 150 agent tasks graded on the files and state the agent leaves behind) | 76.7 | 150 tasks across 25 categories | Frontier agentic | [Hermes Bench (Hermes Index)](https://portal.nousresearch.com/bench) |
| MazeBench (MazeBench: visual spatial reasoning in a 3D open world) | 13 | 100 hidden gems across 256 rooms in one open world | Long-horizon spatial planning, with single puzzles that can take over one hundred moves | [MazeBench Results](https://mazebench.com/blog?post=maze-bench-results) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Chartography (no tools) (Chartography without tools) | 64.4 | 100 specialized chart types | Professional chart reasoning | [Chartography](https://surgehq.ai/blog/chartography) |
| Chartography (tools) (Chartography with image and code tools) | 89.0 | 100 specialized chart types | Professional chart reasoning | [Chartography](https://surgehq.ai/blog/chartography) |
| BenchCAD Vision2Code (no tools) (BenchCAD Vision2Code voxel IoU without tools) | 0.730 | 1,000-file Vision2Code subset | Programmatic CAD generation | [BenchCAD: A comprehensive, industry-standard benchmark for programmatic CAD](https://arxiv.org/abs/2605.10865) |
| BenchCAD Vision2Code (tools) (BenchCAD Vision2Code voxel IoU with tools) | 0.962 | 1,000-file Vision2Code subset | Programmatic CAD generation | [BenchCAD: A comprehensive, industry-standard benchmark for programmatic CAD](https://arxiv.org/abs/2605.10865) |
| OfficeQA | 78.9 | Historical Treasury Bulletin questions | Professional document reasoning | [Claude Opus 5 System Card](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf) |
| AA-MMMU-Pro (Artificial Analysis MMMU-Pro) | 87.7 | Multimodal academic reasoning | Frontier multimodal | [Artificial Analysis MMMU-Pro Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/mmmu-pro) |
| Design Arena Website (Design Arena Website Elo) | 1335 | Website generation comparisons | Design and website generation | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |
| OfficeQA Pro | 67.7 | Document and spreadsheet tasks | Enterprise grounded reasoning | [OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning](https://arxiv.org/abs/2603.08655) |
| Biomedical image analysis (Anthropic biomedical-image-analysis evaluation) | 71.4 | 91 cases across 31 biomedical imaging tasks | Biomedical image analysis | [Claude Opus 5.5 System Card](https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf) |
| ParseBench (ParseBench: document parsing for AI agents (LlamaIndex leaderboard)) | 79.85 | 2,078 human-verified enterprise pages from insurance, finance and government documents | No method is strong on all five dimensions; charts and visual grounding separate the field | [ParseBench: A Document Parsing Benchmark for AI Agents](https://arxiv.org/abs/2604.08538) |
| ExtractBench (LlamaIndex) (ExtractBench: schema-guided enterprise document extraction (LlamaIndex leaderboard)) | 86.06 | 370 documents, 4,869 pages, 8 business domains, 67 document types, each with a JSON Schema | Short documents are near solved; long record lists and grounding separate systems | [ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction](https://arxiv.org/abs/2607.29677) |
| ExtractBench Pro (ExtractBench Pro: long-tail document extraction challenges (LlamaIndex)) | 51 | 100 synthetic documents, 2,622 pages, 86 document types, six challenge groups | The best system completes 58 of 100 documents perfectly; several complete none | [ExtractBench Pro leaderboard and challenge descriptions](https://www.extractbench.ai/pro) |

### Instruction Following

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Gray Swan IPI (15 attempts) (Gray Swan Indirect Prompt Injection, attack success at 15 attempts) | 1.0 | Indirect prompt-injection attacks | Adversarial prompt injection | [Gemini 4 Argon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-argon) |

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

| Event | Type | Confirmation | Announced | Effective | Replacement | Source |
| --- | --- | --- | --- | --- | --- | --- |
| Claude Opus 5.5 | Release | confirmed | Unavailable | 2026-09-22 | — | [Anthropic](https://www.anthropic.com/claude-opus-5-5) |

## What this profile does not claim

Values are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned. Last attempted fetch for this model's score: 2026-10-23 13:17 UTC.