← All models

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)

deprecated by benchmark source
Anthropic · released 2026-02-17 · 14 offers

Context 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.

#ProviderAdjusted $/task
1Google
2Amazon Bedrock
3Azure
4Google Vertex AI
5AWS Bedrock

Composite

6 of 7 inputs · 4 from the model family6 radar axes: DesignArena's two boards share one

71.8

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 73AA Intelligence: percentile 88Epoch ECI: percentile 60Software ECI: percentile 42DesignArena: percentile 47

AA Coding 63.0Coding Agent v1.4 AA Intelligence 30.5AA Agentic Epoch ECI 152.3Software ECI 150.0DesignArena 1205/1223

Radar: percentile among all models measured on each input; a gap means not measured.

Benchmark sheet

39 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Composite attachments (used in the score, not counted as exact benchmarks):
  • Epoch ECI · attached
  • Software ECI · attached
  • DesignArena Web Apps (agentic) · attached
  • DesignArena Full-Stack · attached
Compare this model →

Agentic

  • AA-AnalystAgent4020.0%

    AA-AnalystAgent published 2026-09-10 · Published board — Tests analyst tasks using agentic Python execution across fourteen domains.

  • APEX-Agents-AA5928.0%

    APEX-Agents-AA published 2026-09-10 · Published board — Tests professional-service tasks that require agents to produce locally graded deliverables.

  • AA-Briefcase581,065 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 v2711,295 Elo

    GDPval-AA v2 v2 · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.

  • Harvey LAB-AA5786.0%

    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.

  • ITBench-AA6939.8%

    ITBench-AA published 2026-09-10 · Published board — Tests root-cause diagnosis from offline Kubernetes incident snapshots.

  • Terminal-Bench Hard (AA)9653.0%

    Terminal-Bench Hard (AA) pinned revision 74221fb · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.

  • Terminal-Bench v2.1 (AA)7171.2%

    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)583.0%

    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)02.0%

    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.

  • Vals Index v2 (Vals AI)2750.6%

    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)3351.0%

    Finance Agent v2 (Vals Index v2) v2 · Published board — Multi-step financial reasoning tasks.

  • Terminal-Bench 2.1 (Vals Index v2)2357.3%

    Terminal-Bench 2.1 (Vals Index v2) v2 · Published board — Command-line interface problem solving, as run by Vals AI.

  • HLAB — Harvey's Legal Agent Benchmark (Vals Index v2)425.0%

    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, June 2026 task release (XLANG Lab) v2026.06.24no percentile8.3%

    OSWorld 2.0, June 2026 task release (XLANG Lab) v2026.06.24 · standard — 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.

Coding

  • SciCode (AA subproblems) v1.0.15950.1%

    SciCode (AA subproblems) v1.0.1 · Published board — Tests scientific Python programming with scientist-annotated background information.

  • Vibe Code Bench (Vals Index v2)2651.5%

    Vibe Code Bench (Vals Index v2) v2 · Published board — End-to-end app-building tasks.

  • Code Migration (Vals Index v2 subset)5040.1%

    Code Migration (Vals Index v2 subset) v2 · Published board — Porting projects to another language, including COBOL modernization.

  • FrontierCode 1.1 Main (Cognition) v1.1no percentile24.3%

    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.

  • AA Coding Index7363.0

    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

Instruction-following

Knowledge

Long-context

  • GDP.pdf (AA)6515.8%

    GDP.pdf (AA) published 2026-09-10 · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.

  • AA-LCR v1.18980.0%

    AA-LCR v1.1 v1.1 · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.

  • MLCR-AA7824.4%

    MLCR-AA published 2026-09-10 · Published board — Tests medical-record synthesis and reasoning across long, fragmented case documents.

Reasoning

  • Chess Puzzles (Epoch AI)153.0%

    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.

  • AA Intelligence Index8830.5

    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

Tool-use

Vision

Unusual results

1 threshold-crossing signal flagged · 35 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 strong Terminal-Bench Hard (AA)
    Why
    Observed: 0.5303 fraction
    Peer mean 0.18472 · peer sd 0.16951 · n 432 · families 315
    Directed z 2.039 · baseline z 0.242 · gap 1.797 · profile n 34
    0.5303 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
    Evidence
    Axis: Terminal-Bench Hard (AA) · pinned revision 74221fb · Published board
    Exact value: 0.53030303030303 fraction
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:df8d14e0-3997-4e4d-b4ad-9c047acc9c69:terminalbenchHard
Missing coverage · 104 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)

VariantAA CodingAA Intelligence
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)63.030.5
Claude Sonnet 4.6 (Non-reasoning, High Effort)24.7
Claude Sonnet 4.6 (Non-reasoning, Low Effort)23.3
Claude Sonnet 4.6 (Adaptive Reasoning, Medium Effort)

SUBSCRIPTION PLAN

GitHub Copilot

Current usage-based billing · model token cost is converted to AI Credits at 1 credit = $0.01.

Input $3.00 / 1M
Cached input $0.300 / 1M
Cache write $3.75 / 1M
Output $15.00 / 1M
Status GA

Legacy annual Pro/Pro+ request billing only.

Multiplier 9.00×
Effective cost $0.360 / request

GitHub marks this multiplier as subject to change.

Token offers by platform · 11 offers (Adjusted $/task)

Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.

11 offers within the active global filters; “—” means the catalog is active but no public token price is available.

OpenRouter (7)

Google
Amazon Bedrock
Azure
Amazon Bedrock
Amazon Bedrock
Google
Google

Google Vertex AI (2)

Google Vertex AI
Google Vertex AI

AWS Bedrock (1)

AWS Bedrock

T-Systems LLM Hub (1)

T-Systems LLM Hub
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) — benchmarks & cost | Benchmark Heaven