Claude Opus 4.6
Anthropic · Proprietary · rank 20 · bench-align-v5
Canonical idclaude-opus-4-6
Access typeProprietary
Blended $/1M$10.0075% input / 25% output
Capability shape
Seven axes from the ranking source. A missing axis is drawn as a gap.
Runtime service evidence
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: Observed
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | 2.27 s | 2026-09-17 | 2026-09-17 | |
| Throughput | 37 tok/s | 2026-09-17 | 2026-09-17 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Endpoint and price matrix
Every published price component, including cache reads and writes.
| Component | USD | Evidence |
|---|---|---|
| Input / 1M tokens | $5.00 | |
| Output / 1M tokens | $25.00 | |
| Cache read / 1M tokens | Unavailable | |
| Cache write / 1M tokens | Unavailable | |
| Blended / 1M (75% input / 25% output) | $10.00 |
Self-hosted listingAnthropic public pricing updated for the current Opus tier; Anthropic's April 16, 2026 Claude Opus 4.7 announcement says pricing remains the same as Opus 4.6 at $5/$25 per million tokens.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. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Benchmark record
46 matched benchmark rows with their published value, unit, and provenance.
Knowledge
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| GPQA Graduate-Level Google-Proof Q&A | 91.3 | 448 questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| GPQA-D GPQA Diamond | 89.2 | Graduate-level science questions | Graduate level | Trinity-Large-Thinking: Scaling an Open Source Frontier Agent |
| SuperGPQA SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines | 95 | 285 disciplines | Graduate level | SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines |
| MMLU-Pro Massive Multitask Language Understanding Professional | 82 | Multiple subjects | Professional level | MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark |
| HLE Humanity's Last Exam | 53 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 26.4 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-GPQA Diamond Artificial Analysis GPQA Diamond | 84.0 | Graduate-level science questions | Graduate-level science reasoning | Artificial Analysis GPQA Diamond Benchmark Leaderboard |
| AA-HLE Artificial Analysis Humanity's Last Exam | 19.1 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 2.4 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 45.8 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 80.1 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| HealthBench Hard HealthBench Hard | 14.8 | 1,000 health prompts | Advanced health reasoning | Muse Spark Eval Methodology |
| MedXpertQA (Text) MedXpertQA Text | 52.1 | 2,450 medical multiple-choice questions | Professional medical knowledge | Muse Spark Eval Methodology |
| HLE w/o tools Humanity's Last Exam without tools | 40 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
| MMLU-Pro (Arcee) MMLU-Pro first-party comparison snapshot | 89.1 | Professional academic QA | Professional level | Trinity-Large-Thinking: Scaling an Open Source Frontier Agent |
Coding
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| SWE-bench Verified Software Engineering Benchmark Verified | 80.84 | 500 verified issues | Professional software engineering | SWE-bench: Can Language Models Resolve Real-World GitHub Issues? |
| SWE-Rebench SWE-Rebench | 65.3 | Fresh GitHub issues (rolling window) | Professional software engineering | SWE-Rebench: Contamination-Free Evaluation of Software Engineering Agents |
| LiveCodeBench Pro LiveCodeBench Pro | 70.7 | Quarter-specific contest programming sets | High-end contest programming | LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming? |
| SWE-bench Pro SWE-bench Pro | 53.4 | 1,865 repository problems | Long-horizon professional engineering | SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? |
| FrontierCode 1.1 Main FrontierCode 1.1 Main | 26.9 | 100 private Main tasks (150 in Extended) | Frontier coding-agent quality | FrontierCode leaderboard |
| Vibe Code Bench Vibe Code Bench v1.1 | 57.57 | End-to-end web application builds | End-to-end software delivery | Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development |
| React Native Evals React Native Evals | 84.1 | React Native app implementation tasks | Production mobile app engineering | React Native Evals |
| SWE-bench Verified* SWE-bench Verified (mini-swe-agent-v2) | 75.6 | Repository task completion | Professional software engineering | Trinity-Large-Thinking: Scaling an Open Source Frontier Agent |
Mathematics
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| AIME25 (Arcee) AIME25 first-party comparison snapshot | 99.8 | 15 problems | High school olympiad level | Trinity-Large-Thinking: Scaling an Open Source Frontier Agent |
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 40.700 | 295 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 22.900 | 43 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | FrontierMath Tier 4 v2 leaderboard |
Reasoning
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| AA-LCR Artificial Analysis Long Context Reasoning | 67.0 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| CritPt Critical Physics Tasks | 2.8 | Research-level physics questions | Research-level physics reasoning | CritPt Benchmark Leaderboard |
Instruction Following
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| AA-IFBench Artificial Analysis IFBench | 44.6 | Verifiable instruction constraints | Instruction precision | Artificial Analysis IFBench Benchmark Leaderboard |
Agentic
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 65.4 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| BrowseComp BrowseComp | 83.7 | Research questions requiring browsing | Hard web research | BrowseComp |
| Gert Labs Gert Labs Composite Game Benchmark | 61.85 | Novel game environments | Agentic coding and decision-making | Gert Labs rankings |
| OSWorld-Verified OSWorld-Verified | 72.7 | 369 real-world computer tasks (361 when eight Google Drive tasks are excluded) | Multi-step desktop and cross-application workflows | OSWorld |
| CyberGym CyberGym | 66.6 | 1,507 vulnerability analysis instances | Real-world cybersecurity | CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale |
| JobBench JobBench | 36.7 | 130 tasks across 35 occupations | Professional multi-source workflows | JobBench: Aligning Agent Work With Human Will |
| τ²-bench results τ²-Bench Tool-Agent-User Evaluation | 84.8 | Airline, retail, and telecom customer-service task sets | Dual-control customer-service workflows | τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment |
| DeepSearchQA DeepSearchQA | 73.7 | Agentic browsing and list-answer questions | Agentic web research | Muse Spark Eval Methodology |
| Claw-Eval Claw-Eval | 70.4 | 300 tasks, 2,159 rubrics | Real-world general, multi-turn, and native multimodal agent execution | Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents |
| ResearchClawBench ResearchClawBench | 19.9 | 40 tasks across 10 scientific domains | Scientific research re-discovery | ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research |
| ApprenticeBench ApprenticeBench: end-to-end computer use, continual learning, and long-horizon agency on a real accounts-payable job | 5 | 100 vendor bills processed in sequence inside a simulated construction company | Long-horizon computer use with offline and online continual learning | ApprenticeBench: a step change in AI's job readiness |
Multimodal & Grounded
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| MMMU-Pro Massive Multi-discipline Multimodal Understanding Pro | 77.3 | Multimodal academic reasoning | Frontier multimodal | MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark |
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 72.5 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| Design Arena Website Design Arena Website Elo | 1303 | Website generation comparisons | Design and website generation | OpenRouter Grok 4.3 benchmarks |
| ERQA ERQA | 51.6 | Evidence-based visual QA | Grounded multimodal reasoning | Qwen3.6 launch benchmarks |
| ScreenSpot Pro ScreenSpot Pro | 83.1 | 1,581 grounding instructions | Professional GUI grounding | ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use |
| MedXpertQA (MM) MedXpertQA Multimodal | 64.8 | 2,000 multimodal medical questions | Clinical multimodal reasoning | Muse Spark Eval Methodology |
Lifecycle and limitations log
Lifecycle events the source associates with this model, plus what this profile does not claim.
No lifecycle event references this model.
That is not evidence the model has no lifecycle plan — only that this source published none.
What this profile does not claimValues 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 — the attempt timestamp is in each badge. Last attempted fetch for this model’s score: 2026-09-17 17:17 UTC.