llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsClaude Sonnet 3.5

Anthropic model product

Claude Sonnet 3.5

Claude 3.5 Sonnet is a powerful AI model with industry-leading software engineering skills. It excels in coding, planning, and problem-solving, with significant improvements in agentic coding and tool use tasks. The model includes computer use capabilities in public beta, allowing it to interact with computer interfaces like a human user.

Updated Aug 10, 2026. Default version: Claude 3.5 Sonnet

Compare
LLMBoard score73.4Claude 3.5 Sonnet
Coverage80%8 benchmark families
Context window200KTokens
Official input priceN/AOfficial price unavailable

On this page

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

Model specification

Structured fields from the published default version.

Version
Claude 3.5 Sonnet
Released
Oct 22, 2024
Knowledge cutoff
Apr 30, 2024
Parameters
N/A
Context window
200K
Max output
8.2K
Inputs
image, pdf, text
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.

Claude 3.5 Sonnet category scores

Benchmark results

Published benchmark records for the scored version Claude 3.5 Sonnet.

19 rows
Columns

Show columns

AI2D0.9132100.0%CAug 7, 2026
ChartQA0.9124100.0%CAug 7, 2026
OSWorld Extended0.211100.0%CAug 7, 2026
OSWorld Screenshot-only0.111100.0%CAug 7, 2026
BIG-Bench Hard0.922195.0%CAug 7, 2026
DocVQA1.032692.0%CAug 7, 2026
DROP0.933093.1%CAug 7, 2026
HumanEval0.937697.3%CAug 7, 2026
MGSM0.943190.0%CAug 7, 2026
GSM8k1.074887.2%CAug 7, 2026
MMLU0.9810092.9%CAug 7, 2026
TAU-bench Retail0.7122554.2%CAug 7, 2026
TAU-bench Airline0.5162331.8%CAug 7, 2026
MathVista0.7203950.0%CAug 7, 2026
MATH0.8217171.4%CAug 7, 2026
MMMU0.7356345.2%CAug 7, 2026
MMLU-Pro0.86212952.3%CAug 7, 2026
SWE-Bench Verified0.58910414.6%CAug 7, 2026
GPQA0.713723341.4%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

70 rows
Columns

Show columns

vision style controlchinese761160.0513N/AAug 6, 2026
visionchinese821114.5513N/AAug 6, 2026
vision style controlocr831177.2956N/AAug 6, 2026
vision style controlhomework841170.3223N/AAug 6, 2026
vision style controldiagram851184.4316N/AAug 6, 2026
vision style controloverall901161.110,389N/AAug 6, 2026
visionhomework931137.3223N/AAug 6, 2026
visiondiagram961132.2316N/AAug 6, 2026
visionocr961138.7956N/AAug 6, 2026
vision style controlenglish991154.45,373N/AAug 6, 2026
visionoverall1041125.510,389N/AAug 6, 2026
visionenglish1061124.85,373N/AAug 6, 2026
text style controlpolish1241383.82,195N/AAug 6, 2026
text style controlgerman1351378.91,989N/AAug 6, 2026
text style controlcreative writing1361369.911,748N/AAug 6, 2026
text style controlindustry entertainment and sports and media1391365.014,304N/AAug 6, 2026
text style controlindustry writing and literature and language1411376.221,857N/AAug 6, 2026
text style controljapanese1411308.11,965N/AAug 6, 2026
text style controlcoding1481435.114,955N/AAug 6, 2026
text style controllonger query1501395.013,770N/AAug 6, 2026
text style controlfrench1511390.2812N/AAug 6, 2026
text style controlmulti turn1541388.716,023N/AAug 6, 2026
text style controlrussian1551374.29,926N/AAug 6, 2026
text style controlkorean1581305.11,255N/AAug 6, 2026
text style controlinstruction following1591372.731,256N/AAug 6, 2026
text style controlspanish1591363.9917N/AAug 6, 2026
text style controlhard prompts1621398.427,276N/AAug 6, 2026
text style controlhard prompts english1631405.115,807N/AAug 6, 2026
text style controlindustry legal and government1641382.65,531N/AAug 6, 2026
textjapanese1651233.81,965N/AAug 6, 2026
text style controlnon english1671357.341,858N/AAug 6, 2026
text style controloverall1681373.488,291N/AAug 6, 2026
text style controlexclude ties1691345.361,919N/AAug 6, 2026
text style controlindustry software and it services1691407.825,268N/AAug 6, 2026
text style controlexpert1731370.15,015N/AAug 6, 2026
text style controlenglish1741383.046,425N/AAug 6, 2026
text style controlindustry medicine and healthcare1751383.74,553N/AAug 6, 2026
textgerman1771295.51,989N/AAug 6, 2026
text style controlindustry life and physical and social science1801376.715,627N/AAug 6, 2026
text style controlindustry business and management and financial operations1821353.811,310N/AAug 6, 2026
textpolish1831286.52,195N/AAug 6, 2026
text style controlindustry mathematical1831359.08,619N/AAug 6, 2026
textfrench1841301.7812N/AAug 6, 2026
text style controlmath1881351.110,014N/AAug 6, 2026
textindustry writing and literature and language1891313.221,857N/AAug 6, 2026
textspanish1921283.4917N/AAug 6, 2026
text style controlchinese1931366.56,591N/AAug 6, 2026
textrussian1971304.39,926N/AAug 6, 2026
textmulti turn1981325.616,023N/AAug 6, 2026
textcoding1991342.814,955N/AAug 6, 2026
textkorean1991197.81,255N/AAug 6, 2026
textcreative writing2001291.911,748N/AAug 6, 2026
textindustry mathematical2031306.78,619N/AAug 6, 2026
textmath2061306.610,014N/AAug 6, 2026
textlonger query2071311.913,770N/AAug 6, 2026
textindustry entertainment and sports and media2081279.214,304N/AAug 6, 2026
textinstruction following2091297.431,256N/AAug 6, 2026
texthard prompts2121305.627,276N/AAug 6, 2026
textexpert2141264.05,015N/AAug 6, 2026
textindustry software and it services2141316.625,268N/AAug 6, 2026
textnon english2151281.941,858N/AAug 6, 2026
texthard prompts english2171314.715,807N/AAug 6, 2026
textoverall2211297.888,291N/AAug 6, 2026
textexclude ties2221236.261,919N/AAug 6, 2026
textchinese2251270.56,591N/AAug 6, 2026
textenglish2271307.846,425N/AAug 6, 2026
textindustry business and management and financial operations2371254.311,310N/AAug 6, 2026
textindustry legal and government2401277.35,531N/AAug 6, 2026
textindustry medicine and healthcare2401256.14,553N/AAug 6, 2026
textindustry life and physical and social science2471270.615,627N/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
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No published price snapshot

The default version has no provider offering with current input or output token prices.

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

Claude Sonnet 3.5 versions

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

2 rows
Columns

Show columns

Claude 3.5 SonnetOct 22, 202473.4N/A200K8.2KNoProprietary
Claude 3.5 SonnetJun 21, 2024N/AN/A200K200KNoProprietary

What is Claude Sonnet 3.5?

A concise description based on the published model registry.

Claude 3.5 Sonnet is a powerful AI model with industry-leading software engineering skills. It excels in coding, planning, and problem-solving, with significant improvements in agentic coding and tool use tasks. The model includes computer use capabilities in public beta, allowing it to interact with computer interfaces like a human user.

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.

Claude Sonnet 3.5 vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Claude Sonnet 3.5vsQwen3.5 397B A17BClaude Sonnet 3.5vsNova 2 ProClaude Sonnet 3.5vsGemma 4 31BClaude Sonnet 3.5vsQwen3.7 PlusClaude Sonnet 3.5vsGemini 3 FlashClaude Sonnet 3.5vsQwen3.6 Plus

Models similar to Claude Sonnet 3.5

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

#33-4.2
AN

Claude Opus 4.6

Anthropic

69.2 LLMBoard

DetailsCompare
#13+5.0
AN

Claude Opus 4.7

Anthropic

78.4 LLMBoard

DetailsCompare
#6+9.4
AN

Claude Opus 4.8

Anthropic

82.9 LLMBoard

DetailsCompare
#41-9.8
AN

Claude Sonnet 3.7

Anthropic

63.6 LLMBoard

DetailsCompare
#55-14.6
AN

Claude Opus 3

Anthropic

58.8 LLMBoard

DetailsCompare
#110-32.2
AN

Claude Haiku 3.5

Anthropic

41.2 LLMBoard

DetailsCompare

FAQ

Common questions about Claude Sonnet 3.5.

When was Claude Sonnet 3.5 released?

Claude Sonnet 3.5's default version was released on Oct 22, 2024.

How much does Claude Sonnet 3.5 cost?

No official standard PAYG price is currently available for Claude Sonnet 3.5.

Who created Claude Sonnet 3.5?

Claude Sonnet 3.5 is published under Anthropic in the model registry.

What is the context window for Claude Sonnet 3.5?

The default version has a 200K token context window.

Is Claude Sonnet 3.5 open weight?

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

How many API providers offer Claude Sonnet 3.5?

No published provider offering is currently linked to the default version.

What models should I compare Claude Sonnet 3.5 with?

Nearby ranked alternatives include Qwen3.5 397B A17B, Nova 2 Pro, Gemma 4 31B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai