Claude Opus 5 (Adaptive Reasoning, Max Effort)
Output 53 tokens/sFirst token 28 sContext 1M tokens
Top 5 cheapest providers (Adjusted $/task)
The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.
Within the active global provider, residency and confidentiality filters.
| # | Provider | Platform | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | Amazon Bedrock | OpenRouter | $5.00 | $25.00 | |
| 2 | OpenRouter | $5.00 | $25.00 | ||
| 3 | Azure | OpenRouter | $5.00 | $25.00 | |
| 4 | Azure AI Foundry | Azure AI Foundry | $5.00 | $25.00 | |
| 5 | Google Vertex AI | Google Vertex AI | $5.00 | $25.00 |
Composite
7 of 7 inputs · 4 from the model family6 radar axes: DesignArena's two boards share one96.5
AA Coding 78.0Coding Agent v1.4 67.0AA Intelligence 50.7AA Agentic —Epoch ECI 162.3Software ECI 163.6DesignArena 1278/1311
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
53 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
- Epoch ECI · attached
- Software ECI · attached
- DesignArena Web Apps (agentic) · attached
- DesignArena Full-Stack · attached
Agentic
AA-AnalystAgent9453.8%
AA-AnalystAgent published 2026-09-10 ↗ · Published board — Tests analyst tasks using agentic Python execution across fourteen domains.
AA-Briefcase991,645 Elo
AA-Briefcase published 2026-09-10 ↗ · Published board — Tests multi-week professional knowledge-work projects with linked tasks and large source collections.
GDPval-AA v2991,735 Elo
GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Harvey LAB-AA9393.5%
Harvey LAB-AA published 2026-09-10 ↗ · Published board — Tests legal-work deliverables across practice areas on Harvey's private task set. Artificial Analysis' run, graded by one LLM judge against task rubrics — not the same run or scale as Vals AI's HLAB row.
Terminal-Bench v2.1 (AA)9789.1%
Terminal-Bench v2.1 (AA) v2.1 ↗ · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.
Terminal-Bench v4.0 (AA)9549.0%
Terminal-Bench v4.0 (AA) v4.0 ↗ · Published board — Tests terminal-based work on the 66-task release using mini-SWE-agent v2.4.6.
ApprenticeBench CUA (NeoCognition)7736.0%
ApprenticeBench CUA (NeoCognition) published 2026-09-14 ↗ · Claude Code — A computer-use agent operates the Odoo ERP through its screens across 100 sequential accounts-payable tasks with diminishing mentoring.
ApprenticeBench API (NeoCognition)9249.0%
ApprenticeBench API (NeoCognition) published 2026-09-14 ↗ · Claude Code — An agent completes the same 100 sequential accounts-payable tasks in the Odoo ERP with diminishing mentoring, using dedicated application API calls instead of the screen interface.
Vals Index v2 (Vals AI)9767.2%
Vals Index v2 (Vals AI) v2 ↗ · Published board — GDP-weighted average of agentic model performance across finance, coding and legal tasks.
Finance Agent v2 (Vals Index v2)8058.6%
Finance Agent v2 (Vals Index v2) v2 ↗ · Published board — Multi-step financial reasoning tasks.
HLAB — Harvey's Legal Agent Benchmark (Vals Index v2)536.7%
HLAB — Harvey's Legal Agent Benchmark (Vals Index v2) v2 ↗ · Published board — Long-horizon legal work product creation. Vals AI's run of Harvey's Legal Agent Benchmark, reported as accuracy — not comparable with Artificial Analysis' Harvey LAB-AA row.
OSWorld 2.0, August 2026 task release (XLANG Lab) v2026.08.08no percentile31.4%
OSWorld 2.0, August 2026 task release (XLANG Lab) v2026.08.08 ↗ · batch tool — A computer-use agent completes 108 long-horizon, real-world workflows across 31 self-hosted websites and desktop applications, each taking a person about 1.6 hours.
τ^τ-bench (Hyper-τ), release v1 (Sierra) vrelease-v1no percentile23.9%
τ^τ-bench (Hyper-τ), release v1 (Sierra) vrelease-v1 ↗ · Claude Code — A coding agent builds a working customer-service agent from realistic evidence (policies, transcripts, recordings, a client API), and is scored by how well that agent then serves simulated customers on 53 held-out tasks.
EBR-bench (Earthborne Rangers, Epoch AI)8545.7%
EBR-bench (Earthborne Rangers, Epoch AI) published 2026-09-18 ↗ · Published board — Learning-capability test: models repeatedly play the obscure campaign board game Earthborne Rangers with note-taking, and the score measures whether results improve across playthroughs.
Coding
Artificial Analysis Coding Agent Index v1.48867.0%
Artificial Analysis Coding Agent Index v1.4 v1.4 ↗ · Claude Code — The retained AA Coding Agent Index measures coding-agent systems using the earlier three-component implementation.
Artificial Analysis Coding Agent Index v1.55059.7%
Artificial Analysis Coding Agent Index v1.5 v1.5 ↗ · Claude Code — Measures coding-agent systems on DeepSWE v1.1, Terminal-Bench 4.0 and SWE-Atlas-QnA.
SciCode (AA subproblems) v1.0.18756.4%
SciCode (AA subproblems) v1.0.1 ↗ · Published board — Tests scientific Python programming with scientist-annotated background information.
SWE-bench Multilingualno percentile89.5%
SWE-bench Multilingual published 2026-09-10 ↗ · Published board — A 300-instance SWE-bench variant with tasks from 42 repositories across 9 programming languages.
SWE-bench Multimodalno percentile59.4%
SWE-bench Multimodal published 2026-09-10 ↗ · Published board — A 480-instance SWE-bench variant whose issue descriptions include visual elements.
CursorBench 4.0 (Cursor) v4.0no percentile46.6%
CursorBench 4.0 (Cursor) v4.0 ↗ · Published board — Agent evaluation on ambiguous, multi-file tasks drawn from real Cursor sessions.
Code Migration (Vals Index v2 subset)9456.7%
Code Migration (Vals Index v2 subset) v2 ↗ · Published board — Porting projects to another language, including COBOL modernization.
FrontierCode 1.1 Main (Cognition) v1.1no percentile48.0%
FrontierCode 1.1 Main (Cognition) v1.1 ↗ · claude-code — Whether a maintainer would merge the agent's pull request, on tasks crafted by open-source maintainers and graded with tests, rubrics and verifiers.
DeepSWE (Datacurve, via Epoch AI)9773.6%
DeepSWE (Datacurve, via Epoch AI) published 2026-09-15 ↗ · mini-swe-agent — Pass rate of coding agents on original, long-horizon software engineering tasks, run by Datacurve with the mini-swe-agent harness.
KernelBench-CUDA: GLM-5.2 Fused MoE (RTX PRO 6000) vrtx-pro-600010010.7
KernelBench-CUDA: GLM-5.2 Fused MoE (RTX PRO 6000) vrtx-pro-6000 ↗ · Published board — Fuse GLM-5.2’s MoE forward pass (256+shared experts, top-8 routing) as one CUDA kernel over a frozen shape sweep; Triton, vLLM and other DSLs are banned — CUDA/PTX/CUTLASS only.
KernelBench-CUDA: DeepSeek NSA (RTX PRO 6000) vrtx-pro-600080103.7
KernelBench-CUDA: DeepSeek NSA (RTX PRO 6000) vrtx-pro-6000 ↗ · Published board — Implement DeepSeek’s Native Sparse Attention block (block top-n routing + sparse attention) as a CUDA kernel over a frozen shape sweep.
KernelBench-CUDA: MegaQwen Decode (RTX PRO 6000) vrtx-pro-60001006.55
KernelBench-CUDA: MegaQwen Decode (RTX PRO 6000) vrtx-pro-6000 ↗ · Published board — Improve the known MegaQwen CUDA megakernel geometry for decode-only token throughput at context lengths 2k–128k; prefill is untimed.
KernelBench-CUDA: Grid MinGRU SPS (RTX PRO 6000) vrtx-pro-6000100196.1
KernelBench-CUDA: Grid MinGRU SPS (RTX PRO 6000) vrtx-pro-6000 ↗ · Published board — Non-LLM RL simulation: maximise simulation steps per second for a grid world with a MinGRU agent (roofline anchored at 150M peak SPS); fusion optional.
AA Coding Index9878.0
AA Coding Index published 2026-09-19 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.
Efficiency
CursorBench 4.0 cost per task (Cursor) v4.0no percentile$11.95
CursorBench 4.0 cost per task (Cursor) v4.0 ↗ · Published board — Cursor's published USD cost per task for each CursorBench 4.0 model-effort configuration.
ApprenticeBench CUA cost per task (NeoCognition)54$20.07
ApprenticeBench CUA cost per task (NeoCognition) published 2026-09-14 ↗ · Claude Code — ApprenticeBench's published USD cost per task for each CUA model-harness-effort configuration on the 100-task accounts-payable job.
ApprenticeBench API cost per task (NeoCognition)15$5.28
ApprenticeBench API cost per task (NeoCognition) published 2026-09-14 ↗ · Claude Code — ApprenticeBench's published USD cost per task for each API-board model-harness-effort configuration on the 100-task accounts-payable job.
Vals Index v2 cost per test (Vals AI)10$18.81
Vals Index v2 cost per test (Vals AI) v2 ↗ · Published board — Vals AI's published USD cost per test for each model on the Vals Index v2.
FrontierCode 1.1 Main cost per rollout (Cognition) v1.1no percentile$11.42
FrontierCode 1.1 Main cost per rollout (Cognition) v1.1 ↗ · claude-code — Cognition's published mean USD spend per rollout for each FrontierCode 1.1 Main model and reasoning effort.
Knowledge
Humanity's Last Exam (AA text-only)9954.9%
Humanity's Last Exam (AA text-only) published 2026-09-10 ↗ · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
AA-Omniscience Index9837.1
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
Legal Research Bench (Vals Index v2)9755.3%
Legal Research Bench (Vals Index v2) v2 ↗ · Published board — Case and statute research with citation-backed answers.
SimpleQA Verified (run by Epoch AI)7059.9%
SimpleQA Verified (run by Epoch AI) published 2026-09-16 ↗ · Published board — Short fact-seeking questions answered without tools, testing whether a model knows a fact rather than guessing; Google DeepMind's cleaned version of OpenAI's SimpleQA, run by Epoch AI.
Long-context
GDP.pdf (AA)8221.6%
GDP.pdf (AA) published 2026-09-10 ↗ · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
AA-LCR v1.18779.3%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
MLCR-AA9455.6%
MLCR-AA published 2026-09-10 ↗ · Published board — Tests medical-record synthesis and reasoning across long, fragmented case documents.
Math
ArXivMath 06/2026 (MathArena) v2026-065082.6%
ArXivMath 06/2026 (MathArena) v2026-06 ↗ · Published board — Research-level math problems with a checkable final answer, drawn from arXiv papers submitted in June 2026, so they postdate most training data.
BrokenArXiv 06/2026 (MathArena) v2026-069090.7%
BrokenArXiv 06/2026 (MathArena) v2026-06 ↗ · Published board — Plausible but false proof statements taken from June 2026 arXiv papers; a model scores by refusing to prove them and saying the statement is false as written.
FrontierMath Tiers 1–3 v2 (Epoch AI)8285.6%
FrontierMath Tiers 1–3 v2 (Epoch AI) v2 ↗ · Published board — Unpublished, expert-written mathematics problems from undergraduate to research level with automatically checkable answers, run by Epoch AI on its private v2 set.
FrontierMath Tier 4 v2 (Epoch AI)7273.2%
FrontierMath Tier 4 v2 (Epoch AI) v2 ↗ · Published board — The hardest, research-level tier of Epoch AI's unpublished FrontierMath problems, run by Epoch AI on its private v2 set.
Reasoning
Chess Puzzles (Epoch AI)8342.0%
Chess Puzzles (Epoch AI) published 2026-09-18 ↗ · Published board — Best-move selection on 100 novel chess positions generated programmatically by Epoch AI, each with a single Stockfish-verified best move; probes spatial reasoning and planning.
Mystery Game Puzzles (Epoch AI)9759.0%
Mystery Game Puzzles (Epoch AI) published 2026-09-18 ↗ · Published board — Best-move selection on 100 mid-game positions of a well-known game whose identity Epoch deliberately keeps undisclosed, generated programmatically like Chess Puzzles.
AA Intelligence Index9950.7
AA Intelligence Index published 2026-09-19 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.
Science
CritPt (AA)9829.1%
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)9693.2%
GPQA Diamond (AA) published 2026-09-10 ↗ · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
GPQA Diamond (Epoch AI run)9093.9%
GPQA Diamond (Epoch AI run) published 2026-09-18 ↗ · Published board — Epoch AI's own inspect-ai runs of GPQA Diamond, the 198-question graduate-level science multiple-choice set.
Tool-use
AutomationBench-AA v1.0.68456.6%
AutomationBench-AA v1.0.6 ↗ · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.
EnterpriseOps-Gym-AA8947.5%
EnterpriseOps-Gym-AA published 2026-09-10 ↗ · Published board — Tests enterprise workflows through MCP tools against resettable application environments.
τ³-Banking (AA) v1.0.18942.1%
τ³-Banking (AA) v1.0.1 ↗ · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Excel Modeling Benchmark (Vals Index v2)9473.6%
Excel Modeling Benchmark (Vals Index v2) v2 ↗ · Published board — Building and editing financial models in spreadsheets.
Vision
MMMU Pro (AA)9784.7%
MMMU Pro (AA) published 2026-09-10 ↗ · Published board — Tests multimodal understanding using challenging ten-option questions.
Unusual results
4 threshold-crossing signals flagged · 34 eligible benchmark families
How flags are calculated
Heuristic screen, not statistical significance: benchmark families are correlated and source uncertainty is unknown. Peer evidence needs ≥ 20 independently measured matched configurations from ≥ 10 distinct model families. A flag needs a directed population z-score of magnitude ≥ 1.5 and a gap of ≥ 1.5 from the leave-one-benchmark-family-out mean z in the same direction, over ≥ 5 other benchmark families.
- unusually weak Vals Index v2 cost per test (Vals AI)
Why
Observed: 18.81021 USDPeer mean 7.03053 · peer sd 7.84824 · n 31 · families 30Directed z -1.501 · baseline z 1.376 · gap -2.877 · profile n 3318.81021 USDmeasuredobserved 2026-09-18vals.ai ↗Evidence
Axis: Vals Index v2 cost per test (Vals AI) · v2 · Published boardExact value:18.810212USDObserved: 2026-09-18T13:00:43.826192+00:00 · publication date: not recordedObservation id:public:ffda78fe1c388b1cae263889 - unusually strong CritPt (AA) published 2026-09-10
Why
Observed: 0.29143 fractionPeer mean 0.03928 · peer sd 0.07596 · n 522 · families 369Directed z 3.32 · baseline z 1.23 · gap 2.09 · profile n 330.29143 fractionmeasuredobserved 2026-09-10artificialanalysis.ai ↗Evidence
Axis: CritPt (AA) · published 2026-09-10 · Published boardExact value:0.291428571428571fractionObserved: 2026-09-10T21:47:16.627Z · publication date: not recordedObservation id:aa:b8fc61f7-5e9a-49e6-8547-6ac56db24627:critpt - unusually strong AA Intelligence Index published 2026-09-19
Why
Observed: 50.7 pointsPeer mean 15.94317 · peer sd 11.48893 · n 644 · families 483Directed z 3.025 · baseline z 1.239 · gap 1.786 · profile n 3350.7 pointsmeasuredobserved 2026-09-19artificialanalysis.ai ↗Evidence
Axis: AA Intelligence Index · published 2026-09-19 · Published boardExact value:50.7pointsObserved: 2026-09-19 · publication date: not recordedObservation id:legacy:aa_intelligence_index:claude-opus-5::maxProtocol: inspect · filedata/raw/artificialanalysis.json - unusually strong Humanity's Last Exam (AA text-only) published 2026-09-10
Why
Observed: 0.54866 fractionPeer mean 0.15283 · peer sd 0.14006 · n 608 · families 449Directed z 2.826 · baseline z 1.245 · gap 1.581 · profile n 330.54866 fractionmeasuredobserved 2026-09-10artificialanalysis.ai ↗Evidence
Axis: Humanity's Last Exam (AA text-only) · published 2026-09-10 · Published boardExact value:0.548656163113994fractionObserved: 2026-09-10T21:47:16.627Z · publication date: not recordedObservation id:aa:b8fc61f7-5e9a-49e6-8547-6ac56db24627:hle
Missing coverage · 90 benchmark versions
No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.
Variants / reasoning settings
Artificial Analysis snapshot 2026-09-19 · Data: Artificial Analysis · Data: Epoch AI (CC BY)
| Variant | AA Coding | AA Intelligence |
|---|---|---|
| Claude Opus 5 (Adaptive Reasoning, Max Effort) | 78.0 | 50.7 |
| Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | 77.0 | 49.7 |
| Claude Opus 5 (Adaptive Reasoning, High Effort) | 76.5 | 48.2 |
| Claude Opus 5 (Adaptive Reasoning, Medium Effort) | 74.3 | 45.1 |
| Claude Opus 5 (Adaptive Reasoning, Low Effort) | 66.9 | 39.8 |
| Claude Opus 5 (Non-reasoning) | — | — |
SUBSCRIPTION PLAN
GitHub Copilot
Current usage-based billing · model token cost is converted to AI Credits at 1 credit = $0.01.
Token offers by platform · 13 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
13 offers within the active global filters; “—” means the catalog is active but no public token price is available.
OpenRouter (8)
| Amazon Bedrock | globalamazon-bedrock | $5.00 raw in $/1M | $25.00 raw out $/1M | |
| globalgoogle-vertex/global | $5.00 raw in $/1M | $25.00 raw out $/1M | ||
| Amazon Bedrock | globalamazon-bedrock/us-east-1 | $5.50 raw in $/1M | $27.50 raw out $/1M | |
| Amazon Bedrock | euamazon-bedrock/eu-west-1EU | $5.50 raw in $/1M | $27.50 raw out $/1M | |
| Azure | globalazure/global | $5.00 raw in $/1M | $25.00 raw out $/1M | |
| eugoogle-vertex/europeEU | $5.50 raw in $/1M | $27.50 raw out $/1M | ||
| Azure | globalazure/us | $5.00 raw in $/1M | $25.00 raw out $/1M | |
| globalgoogle-vertex/us | $5.50 raw in $/1M | $27.50 raw out $/1M |
Azure AI Foundry (1)
| Azure AI Foundry | us | $5.00 raw in $/1M | $25.00 raw out $/1M |
Google Vertex AI (2)
| Google Vertex AI | global | $5.00 raw in $/1M | $25.00 raw out $/1M | |
| Google Vertex AI | euEU | $5.50 raw in $/1M | $27.50 raw out $/1M |
AWS Bedrock (1)
| AWS Bedrock | eu-central-1 (EU cross-region inference profile)EU | $5.50 raw in $/1M | $27.50 raw out $/1M |
T-Systems LLM Hub (1)
| T-Systems LLM Hub | euEU | $5.67 raw in $/1M | $28.36 raw out $/1M |