← All models

Claude 4.5 Sonnet (Reasoning)

deprecated by benchmark source
Anthropic · released 2025-09-29 · 9 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
1Azurevia OpenRouter — Price via OpenRouter: OpenRouter's price for Azure's endpoint (https://openrouter.ai/anthropic/claude-sonnet-4.5/providers), collected 2026-11-21.
2Google Vertex AIdirect — Direct price: Google Vertex AI's own price list (https://cloud.google.com/vertex-ai/generative-ai/pricing), collected 2026-11-21.
3Amazon Bedrockvia OpenRouter — Price via OpenRouter: OpenRouter's price for Amazon Bedrock's endpoint (https://openrouter.ai/anthropic/claude-sonnet-4.5/providers), collected 2026-11-21.
4Googlevia OpenRouter — Price via OpenRouter: OpenRouter's price for Google's endpoint (https://openrouter.ai/anthropic/claude-sonnet-4.5/providers), collected 2026-11-21.
5AWS Bedrockdirect — Direct price: AWS Bedrock's own price list (https://aws.amazon.com/bedrock/pricing/), collected 2026-11-21.

Composite

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

23.8

includes −2.9 for its Benchmaxxing signal (from 26.7; why, switch off in Options)

AA Coding v4.xCoding Agent v1.4AA Intelligence (est.)AA AgenticEpoch ECISoftware ECIDesignArenaAA Coding v4.x: percentile 59AA Intelligence (est.): percentile 65AA Agentic: percentile 55Epoch ECI: percentile 33Software ECI: percentile 24DesignArena: percentile 9

AA Coding v4.x 52.1Coding Agent v1.4 —AA Intelligence (est.) 9.8AA Agentic 17.5Epoch ECI 147.6Software ECI 148.2DesignArena 1041/1024

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

Benchmark sheet

22 of 320 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-Briefcase32712 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 v247989 Elo

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

  • Terminal-Bench Hard (AA)8235.6%

    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)5655.8%

    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)180.0%

    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.

  • τ²-Bench Airline (OpenRouter run)6073.0%

    τ²-Bench Airline (OpenRouter run) published 2026-09-15 → · Published board — Multi-turn service agents making tool calls under strict policy constraints. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)

  • AA Agentic Index5517.5

    AA Agentic Index published 2026-09-18 → · Published board — Artificial Analysis publishes one Agentic Index per model, measured on its primary configuration and relayed by OpenRouter's Benchmarks API; the value is attached at family scope on the deterministic representative. Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

Coding

  • SciCode (AA subproblems) v1.0.14145.7%

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

  • AA Coding Index v4.x · frozen 2026-10-275952.1

    AA Coding Index v4.x · frozen 2026-10-27 → · Published board — Artificial Analysis withdrew the Coding Index with Intelligence Index v5.0 (2026-10-28). These are the last v4.x values, frozen with their own date (2026-10-27).

  • DesignArena Web Apps (agentic)71,041 Elo

    DesignArena Web Apps (agentic) published 2026-11-17 → · Published board — Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.

  • DesignArena Full-Stack161,024 Elo

    DesignArena Full-Stack published 2026-11-17 → · Published board — Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.

Efficiency

Instruction-following

Knowledge

Long-context

  • GDP.pdf (AA)315.2%

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

  • AA-LCR v1.17072.3%

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

Math

  • AIME 2025 (AA)8688.0%

    AIME 2025 (AA) v2025 → · Published board — Advanced mathematical problem solving on AIME I and II 2025.

Science

Tool-use

  • AutomationBench-AA v1.0.63914.1%

    AutomationBench-AA v1.0.6 → · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.

  • τ²-Bench Telecom (AA)6878.1%

    τ²-Bench Telecom (AA) published 2026-09-10 → · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.

  • τ³-Banking (AA) v1.0.15924.5%

    τ³-Banking (AA) v1.0.1 → · Published board — Tests banking support agents that retrieve policies and change account state through tools.

Vision

Unusual results

2 threshold-crossing signals flagged · 25 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 GPQA Diamond (OpenRouter run) — measured cost per task published 2026-09-15
    Why
    Observed: 0.31611 USD
    Peer mean 0.07402 · peer sd 0.13134 · n 120 · families 120
    Directed z -1.843 · baseline z 0.086 · gap -1.929 · profile n 24
    0.31611 USDmeasured· 1386 tasks· 0.32 USD per task (measured by OpenRouter)observed 2026-09-15openrouter.ai ↗
    Evidence
    Axis: GPQA Diamond (OpenRouter run) — measured cost per task · published 2026-09-15 · Published board
    Exact value: 0.31610685642135644 USD
    Tasks evaluated: 1386
    Published mean cost: 0.31610685642135644 USD per task (measured by OpenRouter) — measured by OpenRouter on GPQA Diamond (OpenRouter run) — measured cost per task
    Observed: 2026-09-15T23:29:03.209Z · publication date: not recorded
    Observation id: openrouter-cost:anthropic/claude-4.5-sonnet-20250929|gpqa_diamond
  • unusually weak DesignArena Web Apps (agentic) published 2026-11-17
    Why
    Observed: 1041 Elo
    Peer mean 1189.01754 · peer sd 86.75019 · n 57 · families 55
    Directed z -1.706 · baseline z 0.08 · gap -1.786 · profile n 24
    1041 Elomeasured1503 battlesobserved 2026-11-17designarena.ai ↗
    Evidence
    Axis: DesignArena Web Apps (agentic) · published 2026-11-17 · Published board
    Exact value: 1041 Elo
    Observed: 2026-11-17 · publication date: not recorded
    Observation id: legacy:frontend:claude-sonnet-4.5::reasoning
    Protocol: inspect · file data/raw/designarena.json
Missing coverage · 298 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 2026-11-04 · Intelligence Index v5.0 (est. = estimated from v4, not measured) · Coding Index v4.x frozen 2026-10-27 · Data: Artificial Analysis · Data: Epoch AI (CC BY)

VariantAA CodingAA Intelligence
Claude 4.5 Sonnet (Reasoning)52.19.8est.
Claude 4.5 Sonnet (Non-reasoning)—9.6est.
Token offers by platform · 6 offers (Adjusted $/task)

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

6 offers within the active global filters, 3 more outside them; “price n/a” means the provider serves the model but publishes no direct token price we could collect — no other channel's price is shown in its place.

OpenRouter (3)

Prices via OpenRouter — what OpenRouter charges for each provider's endpoint, not the provider's own direct price. Source: openrouter.ai/anthropic/claude-sonnet-4.5/providers, collected 2026-11-21.

Azure
Amazon Bedrockconditional
Googleconditional

Google Vertex AI (2)

Direct prices from Google Vertex AI's own price list. Source: cloud.google.com/vertex-ai/generative-ai/pricing, collected 2026-11-21.

Google Vertex AI
Google Vertex AI

AWS Bedrock (1)

Direct prices from AWS Bedrock's own price list. Source: aws.amazon.com/bedrock/pricing/, collected 2026-11-21.

AWS Bedrock
Claude 4.5 Sonnet (Reasoning) — benchmarks & cost