llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsClaude Sonnet 4.5

Anthropic model product

Claude Sonnet 4.5

Claude Sonnet 4.5 is the best coding model in the world. It's the strongest model for building complex agents. It’s the best model at using computers. And it shows substantial gains in reasoning and math. Highest intelligence across most tasks with exceptional agent and coding capabilities.

Updated Aug 10, 2026. Default version: Claude Sonnet 4.5

Compare
LLMBoard scoreN/ANot scored
CoverageN/ANo published score
Context window200KTokens
Official input price$3Anthropic API

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Claude Sonnet 4.5
Released
Sep 29, 2025
Knowledge cutoff
Jan 31, 2025
Parameters
N/A
Context window
200K
Max output
64K
Inputs
audio, image, pdf, text, video
Outputs
text
Open weights
No
License
Proprietary

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

No capability profile

No published version under this unique model currently has enough benchmark coverage to calculate a score.

Benchmark results

Published benchmark records for the scored version currently unavailable.

No benchmark rows

No published benchmark result is linked to the scored version.

Arena results

Preference and agent-evaluation signals from published Arena datasets.

92 rows
Columns

Show columns

text factualitykorean181403.1545N/AAug 6, 2026
text factualityspanish211453.51,264N/AAug 6, 2026
documentoverall221446.228,634N/AJul 30, 2026
text factualitylonger query221486.318,206N/AAug 6, 2026
textlonger query241476.224,698N/AAug 6, 2026
text factualitycoding241522.112,868N/AAug 6, 2026
text factualitygerman251407.1577N/AAug 6, 2026
text style controlcreative writing251453.011,896N/AAug 6, 2026
document style controloverall271446.428,634N/AJul 30, 2026
text factualityhard prompts english281496.216,141N/AAug 6, 2026
text factualityinstruction following281466.716,226N/AAug 6, 2026
text style controllonger query281483.124,698N/AAug 6, 2026
textinstruction following301458.523,108N/AAug 6, 2026
text factualitycreative writing301445.37,288N/AAug 6, 2026
text style controlspanish301465.22,159N/AAug 6, 2026
textcoding311485.419,024N/AAug 6, 2026
textmulti turn321464.814,082N/AAug 6, 2026
text factualitymulti turn321473.28,821N/AAug 6, 2026
textcreative writing331440.611,896N/AAug 6, 2026
text factualityindustry entertainment and sports and media331437.39,755N/AAug 6, 2026
text factualityindustry writing and literature and language331449.711,780N/AAug 6, 2026
textspanish341455.72,159N/AAug 6, 2026
text factualityfrench341474.51,194N/AAug 6, 2026
texthard prompts english351470.523,149N/AAug 6, 2026
text factualityexpert351488.03,411N/AAug 6, 2026
text style controlindustry entertainment and sports and media351442.315,151N/AAug 6, 2026
text style controlindustry writing and literature and language351453.718,215N/AAug 6, 2026
text factualityindustry software and it services361496.823,081N/AAug 6, 2026
text style controlcoding361513.319,024N/AAug 6, 2026
text style controlinstruction following361462.623,108N/AAug 6, 2026
text style controlmulti turn361478.614,082N/AAug 6, 2026
textindustry entertainment and sports and media371426.715,151N/AAug 6, 2026
text style controlhard prompts english371490.123,149N/AAug 6, 2026
text factualityindustry mathematical381446.82,503N/AAug 6, 2026
textindustry writing and literature and language391441.318,215N/AAug 6, 2026
text factualityhard prompts391480.343,052N/AAug 6, 2026
text factualityindustry business and management and financial operations391459.59,453N/AAug 6, 2026
text factualitypolish391403.81,276N/AAug 6, 2026
textexpert401472.45,542N/AAug 6, 2026
texthard prompts401461.846,202N/AAug 6, 2026
textindustry software and it services411472.129,528N/AAug 6, 2026
text style controlindustry business and management and financial operations431460.615,291N/AAug 6, 2026
textindustry business and management and financial operations441439.315,291N/AAug 6, 2026
text factualityrussian441458.44,693N/AAug 6, 2026
text style controlindustry software and it services441497.829,528N/AAug 6, 2026
text factualityindustry legal and government451466.03,356N/AAug 6, 2026
text style controlhard prompts451483.446,202N/AAug 6, 2026
text style controlenglish471467.838,268N/AAug 6, 2026
text style controlexpert471484.55,542N/AAug 6, 2026
text factualityenglish481462.234,946N/AAug 6, 2026
text factualitychinese491485.02,464N/AAug 6, 2026
text style controlfrench491476.71,818N/AAug 6, 2026
text style controlkorean501413.61,252N/AAug 6, 2026
textenglish511451.038,268N/AAug 6, 2026
textindustry legal and government541448.95,726N/AAug 6, 2026
text style controlexclude ties541458.458,728N/AAug 6, 2026
text style controlindustry legal and government541463.45,726N/AAug 6, 2026
textfrench551457.01,818N/AAug 6, 2026
text factualityoverall551447.975,135N/AAug 6, 2026
text style controloverall551454.980,284N/AAug 6, 2026
text style controlrussian551452.77,853N/AAug 6, 2026
text factualityindustry life and physical and social science571466.17,905N/AAug 6, 2026
text factualityindustry medicine and healthcare571469.53,120N/AAug 6, 2026
text style controlindustry life and physical and social science571472.213,002N/AAug 6, 2026
text style controlnon english571439.341,966N/AAug 6, 2026
textkorean581394.91,252N/AAug 6, 2026
text factualityexclude ties581447.654,745N/AAug 6, 2026
textrussian591435.17,853N/AAug 6, 2026
text style controlindustry medicine and healthcare591472.85,104N/AAug 6, 2026
text style controlgerman601445.31,297N/AAug 6, 2026
textindustry mathematical611445.13,953N/AAug 6, 2026
text style controljapanese611410.7683N/AAug 6, 2026
textexclude ties621432.758,728N/AAug 6, 2026
textoverall631437.780,284N/AAug 6, 2026
webdevwebdev-react631383.54,935N/AAug 6, 2026
text style controlindustry mathematical641451.83,953N/AAug 6, 2026
text factualitymath651425.62,852N/AAug 6, 2026
textjapanese671390.4683N/AAug 6, 2026
textindustry life and physical and social science681447.113,002N/AAug 6, 2026
text factualitynon english691432.238,900N/AAug 6, 2026
text style controlpolish691438.72,197N/AAug 6, 2026
webdevoverall691385.015,081N/AAug 6, 2026
webdevwebdev691385.015,081N/AAug 6, 2026
webdevwebdev-html691389.910,126N/AAug 6, 2026
textnon english701422.641,966N/AAug 6, 2026
textgerman741423.71,297N/AAug 6, 2026
text style controlchinese771480.43,835N/AAug 6, 2026
textindustry medicine and healthcare801441.25,104N/AAug 6, 2026
textpolish821414.72,197N/AAug 6, 2026
textchinese851464.43,835N/AAug 6, 2026
text style controlmath881427.74,877N/AAug 6, 2026
textmath991421.74,877N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$3 input, $15 output per 1M
Official provider
Anthropic
Lowest third-party
From $0.43 input, $2.14 output per 1M via QiHang
Tracked offerings
8
8 rows
Columns

Show columns

QiHangclaude-sonnet-4-5-20250929global$0.43$2.14200KAug 7, 2026
Jiekou.AIclaude-sonnet-4-5-20250929global$2.7$13.5200KAug 7, 2026
NanoGPTclaude-sonnet-4-5-20250929global$3$151MAug 7, 2026
LLM Gatewayclaude-sonnet-4-5-20250929global$3$15200KAug 7, 2026
302.AIclaude-sonnet-4-5-20250929global$3$15200KAug 7, 2026
Heliconeclaude-sonnet-4-5-20250929global$3$15200KAug 7, 2026
Abacusclaude-sonnet-4-5-20250929global$3$15200KAug 7, 2026
Anthropicclaude-sonnet-4-5-20250929global$3$151MAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Claude Sonnet 4.5 versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Claude Sonnet 4.5Sep 29, 2025N/AN/A200K64KNoProprietary

What is Claude Sonnet 4.5?

A concise description based on the published model registry.

Claude Sonnet 4.5 is the best coding model in the world. It's the strongest model for building complex agents. It’s the best model at using computers. And it shows substantial gains in reasoning and math. Highest intelligence across most tasks with exceptional agent and coding capabilities.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Models similar to Claude Sonnet 4.5

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#129
AN

Claude Haiku 3

Anthropic

34.1 LLMBoard

DetailsCompare
#114
AN

Claude Sonnet 3

Anthropic

40.0 LLMBoard

DetailsCompare
#110
AN

Claude Haiku 3.5

Anthropic

41.2 LLMBoard

DetailsCompare
#55
AN

Claude Opus 3

Anthropic

58.8 LLMBoard

DetailsCompare
#41
AN

Claude Sonnet 3.7

Anthropic

63.6 LLMBoard

DetailsCompare
#33
AN

Claude Opus 4.6

Anthropic

69.2 LLMBoard

DetailsCompare

FAQ

Common questions about Claude Sonnet 4.5.

When was Claude Sonnet 4.5 released?

Claude Sonnet 4.5's default version was released on Sep 29, 2025.

How much does Claude Sonnet 4.5 cost?

Claude Sonnet 4.5's official API price is $3 per million input tokens and $15 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $0.43 input and $2.14 output via QiHang.

Who created Claude Sonnet 4.5?

Claude Sonnet 4.5 is published under Anthropic in the model registry.

What is the context window for Claude Sonnet 4.5?

The default version has a 200K token context window.

Is Claude Sonnet 4.5 open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Claude Sonnet 4.5?

8 published provider offerings are linked to the default version.

What models should I compare Claude Sonnet 4.5 with?

No nearby ranked alternatives are currently available.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai