Claude 4.5 Sonnet (Reasoning)
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.
| # | Provider | Platform | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | Amazon Bedrock | OpenRouter | $3.30 | $16.50 | |
| 2 | OpenRouter | $3.30 | $16.50 | ||
| 3 | Google Vertex AI | Google Vertex AI | $3.00 | $15.00 | |
| 4 | AWS Bedrock | AWS Bedrock | $3.30 | $16.50 | |
| 5 | Azure | OpenRouter | $3.00 | $15.00 |
Composite
6 of 7 inputs · 4 from the model family6 radar axes: DesignArena's two boards share one51.2
includes −2.5 for its Benchmaxxing signal (from 53.8; why, switch off in Options)
AA Coding 52.1Coding Agent v1.4 —AA Intelligence 21.2AA Agentic 17.5Epoch ECI 146.8Software ECI 147.7DesignArena 1075/1060
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
23 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-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)5555.8%
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)6173.0%
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 Index5117.5
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) v1.0.14645.7%
SciCode (AA subproblems) v1.0.1 ↗ · Published board — Tests scientific Python programming with scientist-annotated background information.
AA Coding Index5952.1
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.
DesignArena Web Apps (agentic)91,075 Elo
DesignArena Web Apps (agentic) published 2026-09-19 ↗ · Published board — Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.
DesignArena Full-Stack171,060 Elo
DesignArena Full-Stack published 2026-09-19 ↗ · Published board — Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.
Efficiency
GPQA Diamond (OpenRouter run) — measured cost per task3$0.32
GPQA Diamond (OpenRouter run) — measured cost per task published 2026-09-15 ↗ · Published board — Mean USD OpenRouter actually spent per task while running GPQA Diamond for this configuration.
τ²-Bench Airline (OpenRouter run) — measured cost per task15$0.33
τ²-Bench Airline (OpenRouter run) — measured cost per task published 2026-09-15 ↗ · Published board — Mean USD OpenRouter actually spent per task while running τ²-Bench Airline for this configuration.
Instruction-following
IFBench (AA single-turn)6957.3%
IFBench (AA single-turn) published 2026-09-10 ↗ · Published board — Tests precise single-turn instructions with deterministic rule checks.
Knowledge
Humanity's Last Exam (AA text-only)6917.8%
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 Index81-0.08
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
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 v1.17272.3%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Math
AIME 2025 (AA) v20258688.0%
AIME 2025 (AA) v2025 ↗ · Published board — Advanced mathematical problem solving on AIME I and II 2025.
Reasoning
AA Intelligence Index7221.2
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)651.1%
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)7383.4%
GPQA Diamond (AA) published 2026-09-10 ↗ · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
GPQA Diamond (OpenRouter run)5782.5%
GPQA Diamond (OpenRouter run) published 2026-09-15 ↗ · Published board — Graduate-level science questions that resist retrieval and reward careful reasoning. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)
Tool-use
AutomationBench-AA v1.0.64214.1%
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) v1.0.16024.5%
τ³-Banking (AA) v1.0.1 ↗ · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Vision
MMMU Pro (AA)4768.7%
MMMU Pro (AA) published 2026-09-10 ↗ · Published board — Tests multimodal understanding using challenging ten-option questions.
Unusual results
2 threshold-crossing signals flagged · 26 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 USDPeer mean 0.07408 · peer sd 0.13073 · n 124 · families 124Directed z -1.851 · baseline z 0.122 · gap -1.973 · profile n 250.31611 USDmeasured· 1386 tasksobserved 2026-09-15openrouter.ai ↗Evidence
Axis: GPQA Diamond (OpenRouter run) — measured cost per task · published 2026-09-15 · Published boardExact value:0.31610685642135644USDTasks evaluated: 1386Observed: 2026-09-15T23:29:03.209Z · publication date: not recordedObservation id:openrouter-cost:anthropic/claude-4.5-sonnet-20250929|gpqa_diamondSource: https://openrouter.ai/benchmarks - unusually weak DesignArena Web Apps (agentic) published 2026-09-19
Why
Observed: 1075 EloPeer mean 1198.82222 · peer sd 77.91656 · n 45 · families 44Directed z -1.589 · baseline z 0.111 · gap -1.701 · profile n 251075 Elomeasured1503 battlesobserved 2026-09-19designarena.ai ↗Evidence
Axis: DesignArena Web Apps (agentic) · published 2026-09-19 · Published boardExact value:1075EloObserved: 2026-09-19 · publication date: not recordedObservation id:legacy:frontend:claude-sonnet-4.5::reasoningProtocol: inspect · filedata/raw/designarena.json
Missing coverage · 118 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 4.5 Sonnet (Reasoning) | 52.1 | 21.2 |
| Claude 4.5 Sonnet (Non-reasoning) | — | 19.3 |
Token offers by platform · 8 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
8 offers within the active global filters; “—” means the catalog is active but no public token price is available.
OpenRouter (5)
| Amazon Bedrock | euamazon-bedrock/eu-west-1EU | $3.30 raw in $/1M | $16.50 raw out $/1M | |
| globalgoogle-vertex/us-east5 | $3.30 raw in $/1M | $16.50 raw out $/1M | ||
| Amazon Bedrock | globalamazon-bedrock | $3.00 raw in $/1M | $15.00 raw out $/1M | |
| globalgoogle-vertex/global | $3.00 raw in $/1M | $15.00 raw out $/1M | ||
| Azure | globalazure/global | $3.00 raw in $/1M | $15.00 raw out $/1M |
Google Vertex AI (2)
| Google Vertex AI | global | $3.00 raw in $/1M | $15.00 raw out $/1M | |
| Google Vertex AI | europe-west1EU | $3.30 raw in $/1M | $16.50 raw out $/1M |
AWS Bedrock (1)
| AWS Bedrock | eu-central-1 (EU cross-region inference profile)EU | $3.30 raw in $/1M | $16.50 raw out $/1M |