Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Anthropic · Proprietary · rank 60 · bench-align-v5
Claude Opus 4.6 is a general-purpose language model. It ranks in the top quarter for knowledge (top 8% of 283 scored models), by BenchLM's published scores. It accepts text, images and PDFs and produces text.
Claude Opus 4.6 by Anthropic scores 59.8 overall, costs $5.00 per 1M input tokens and $25.00 per 1M output tokens, and carries a context window of 1M tokens — observed 2026-11-21.
Seven axes from the ranking source. A missing axis is drawn as a gap.
Every published price component, including cache reads and writes.
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.
Lifecycle events the source associates with this model, plus what this profile does not claim.
Each axis shows the ranking source’s score and, beside it, BenchLM’s separate verified score for that axis. The two are published side by side and are not interchangeable.
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 | 2.24 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 43 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Plans from the model's maker, and the API providers that list this exact model today. Links leave ModelScale; each provider sets its own prices and limits.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| GPQA Graduate-Level Google-Proof Q&A | 91.3 | #25 | 448 questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| GPQA-D GPQA Diamond | 89.2 | #43 | Graduate-level science questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| SuperGPQA SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines | 95 | #1 | 285 disciplines | Graduate level | SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines |
| MMLU-Pro Massive Multitask Language Understanding Professional | 82 | #34 | Multiple subjects | Professional level | MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark |
| HLE Humanity's Last Exam | 53 | #20 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 26.4 | #77 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-GPQA Diamond Artificial Analysis GPQA Diamond | 84.0 | #90 | Graduate-level science questions | Graduate-level science reasoning | Artificial Analysis GPQA Diamond Benchmark Leaderboard |
| AA-HLE Artificial Analysis Humanity's Last Exam | 19.1 | #122 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 2.4 | #66 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 45.8 | #41 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 80.1 | #86 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| HealthBench Hard HealthBench Hard | 14.8 | #13 | 1,000 health prompts | Advanced health reasoning | Muse Spark Eval Methodology |
| MedXpertQA (Text) MedXpertQA Text | 52.1 | #4 | 2,450 medical multiple-choice questions | Professional medical knowledge | Muse Spark Eval Methodology |
| HLE w/o tools Humanity's Last Exam without tools | 40 | #31 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
| MMLU-Pro (Arcee) MMLU-Pro first-party comparison snapshot | 89.1 | #1 | Professional academic QA | Professional level | Trinity-Large-Thinking: Scaling an Open Source Frontier Agent |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 65.4 | #31 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| SWE-bench Verified Software Engineering Benchmark Verified | 80.84 | #15 | 500 verified issues | Professional software engineering | SWE-bench: Can Language Models Resolve Real-World GitHub Issues? |
| SWE-Rebench SWE-Rebench | 65.3 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AIME25 (Arcee) AIME25 first-party comparison snapshot | 99.8 | #1 | 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 | 65.965 | #33 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 26.829 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| ARC-AGI-3 Abstraction and Reasoning Corpus for AGI v3 | 0.51 | #16 | Interactive game-like tasks with hidden rules | Frontier agentic reasoning | ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence |
| AA-LCR Artificial Analysis Long Context Reasoning | 67.0 | #135 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| CritPt Critical Physics Tasks | 2.8 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-IFBench Artificial Analysis IFBench | 44.6 | #92 | Verifiable instruction constraints | Instruction precision | Artificial Analysis IFBench Benchmark Leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 65.4 | #32 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| BrowseComp BrowseComp | 83.7 | #21 | Research questions requiring browsing | Hard web research | BrowseComp |
| Gert Labs Gert Labs Composite Game Benchmark | 61.85 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| MMMU-Pro Massive Multi-discipline Multimodal Understanding Pro | 77.3 | #30 | Multimodal academic reasoning | Frontier multimodal | MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark |
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 72.5 | #72 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| Design Arena Website Design Arena Website Elo | 1280 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chess Puzzles Chess Puzzles (Epoch AI) | 21.0 | #58 | 100 programmatically generated chess positions with a single best move | Novel chess positions, single best move | Chess Puzzles (Epoch AI) |
| Mystery Game Puzzles Mystery Game Puzzles (Epoch AI) | 25.0 | #40 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | Mystery Game Puzzles (Epoch AI) |
| Furniture Assembly Furniture Assembly Benchmark (Epoch AI) | 28.3 |
A second, independent score source. Epoch’s own figures in Epoch’s units, one line per model version Epoch evaluated (effort setting as Epoch labels it). They are not part of this site’s capability scores or rank.
Source: Epoch AI, CC BY 4.0 (licence), benchmark data read once a day.
| #1 |
| Fresh GitHub issues (rolling window) |
| Professional software engineering |
| SWE-Rebench: Contamination-Free Evaluation of Software Engineering Agents |
| LiveCodeBench Pro LiveCodeBench Pro | 70.7 | #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 | #63 | 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 | #16 | 100 private Main tasks (150 in Extended) | Frontier coding-agent quality | FrontierCode leaderboard |
| Vibe Code Bench Vibe Code Bench v1.1 | 57.57 | #7 | 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 | #5 | React Native app implementation tasks | Production mobile app engineering | React Native Evals |
| SWE-bench Verified* SWE-bench Verified (mini-swe-agent-v2) | 75.6 | #1 | Repository task completion | Professional software engineering | Trinity-Large-Thinking: Scaling an Open Source Frontier Agent |
| PostTrainBench v1 PostTrainBench v1 (archived) | 23.2 | #5 | Post-training four base models on seven benchmarks | Autonomous ML engineering | PostTrainBench v1 leaderboard (archived) |
| #35 |
| 41 private extreme-difficulty mathematics problems |
| Research-level mathematics requiring hours or days of expert work |
| FrontierMath Tier 4 v2 leaderboard |
| #105 |
| Research-level physics questions |
| Research-level physics reasoning |
| CritPt Benchmark Leaderboard |
| Novel game environments |
| Agentic coding and decision-making |
| Gert Labs rankings |
| OSWorld-Verified OSWorld-Verified | 72.7 | #22 | 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 | #26 | 1,507 vulnerability analysis instances | Real-world cybersecurity | CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale |
| JobBench JobBench | 36.7 | #23 | 130 tasks across 35 occupations | Professional multi-source workflows | JobBench: Aligning Agent Work With Human Will |
| AndroidWorld AndroidWorld | 62.0 | #10 | Android app workflows | Complex mobile task completion | GLM-5V-Turbo |
| τ²-bench results τ²-Bench Tool-Agent-User Evaluation | 84.8 | #60 | 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 | #20 | Agentic browsing and list-answer questions | Agentic web research | Muse Spark Eval Methodology |
| Claw-Eval Claw-Eval | 70.4 | #9 | 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 | #4 | 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 | #17 | 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 |
| #24 |
| Website generation comparisons |
| Design and website generation |
| OpenRouter Grok 4.3 benchmarks |
| ERQA ERQA | 51.6 | #17 | Evidence-based visual QA | Grounded multimodal reasoning | Qwen3.6 launch benchmarks |
| ScreenSpot Pro ScreenSpot Pro | 83.1 | #8 | 1,581 grounding instructions | Professional GUI grounding | ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use |
| MedXpertQA (MM) MedXpertQA Multimodal | 64.8 | #7 | 2,000 multimodal medical questions | Clinical multimodal reasoning | Muse Spark Eval Methodology |
| ParseBench-1 ParseBench-1: document parsing for AI agents (LlamaIndex leaderboard, first release) | 53.80 | #33 | 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 |
| #31 |
| 60 photos of three IKEA builds, some with deliberate assembly mistakes |
| Spatial reasoning from technical diagrams to real photos |
| Furniture Assembly Benchmark (Epoch AI) |
| EBR-bench Earthborne Rangers (EBR-bench) | 12.7 | #25 | Ten playthroughs of an Earthborne Rangers campaign segment per sample (eight learning, two scored) | Learning an unfamiliar game over multi-hour playthroughs | Earthborne Rangers (EBR-bench), Epoch AI |
| MirrorCode MirrorCode (Epoch AI and METR) | 33.3 | #28 | 30 reimplementation tasks (15 programs in two languages), three attempts each | Days-long software engineering without source code | MirrorCode (Epoch AI) |
| Clocktower Bench Clocktower Bench (Blood on the Clocktower) | 1432 | #8 | 386 rated head-to-head games of Blood on the Clocktower (10 to 12 players) | Social deduction, deception and multi-agent reasoning | Clocktower Bench leaderboard |
| BinaryAudit BinaryAudit (backdoor detection in compiled binaries) | 49.1 | #1 | 19 backdoor and timebomb detection tasks on stripped binaries, three runs each (57 runs); 6 tooling and 8 clean-binary tasks reported alongside | Reverse engineering without source code or symbols | We hid backdoors in ~40 MB binaries and asked AI + Ghidra to find them (Quesma) |
| NYT Connections NYT Connections LLM Benchmark (extended version) | 43.2 | #72 | 940 NYT Connections puzzles, each with up to four added trick words | Wordplay, word knowledge and decoys that fit almost-but-not-quite | NYT Connections LLM Benchmark (Lech Mazur, GitHub) |
| SkillsBench official leaderboard (BenchFlow) SkillsBench v1.1 official leaderboard (BenchFlow) | 50.2 | #12 | 87 tasks in 8 domains (SkillsBench v1.1) | Multi-step agent tasks | SkillsBench leaderboard |