llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsClaude Sonnet 3

Anthropic model product

Claude Sonnet 3

Claude 3 Sonnet strikes the ideal balance between intelligence and speed—particularly for enterprise workloads. It delivers strong performance at a lower cost compared to its peers, and is engineered for high endurance in large-scale AI deployments.

Updated Aug 10, 2026. Default version: Claude 3 Sonnet

Compare
LLMBoard score40.0Claude 3 Sonnet
Coverage80%10 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 Sonnet
Released
Feb 29, 2024
Knowledge cutoff
Unknown
Parameters
N/A
Context window
200K
Max output
200K
Inputs
image, 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 Sonnet category scores

Benchmark results

Published benchmark records for the scored version Claude 3 Sonnet.

11 rows
Columns

Show columns

HellaSwag0.952784.6%CAug 7, 2026
ARC-C0.963484.8%CAug 7, 2026
BIG-Bench Hard0.882165.0%CAug 7, 2026
DROP0.8173044.8%CAug 7, 2026
MGSM0.8173146.7%CAug 7, 2026
GSM8k0.9194861.7%CAug 7, 2026
HumanEval0.7607621.3%CAug 7, 2026
MATH0.4637111.4%CAug 7, 2026
MMLU0.86710033.3%CAug 7, 2026
MMLU-Pro0.610612918.0%CAug 7, 2026
GPQA0.420323312.9%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

64 rows
Columns

Show columns

vision style controlchinese100979.8915N/AAug 6, 2026
visionchinese101937.0915N/AAug 6, 2026
visionoverall132984.012,314N/AAug 6, 2026
vision style controloverall1321017.112,314N/AAug 6, 2026
vision style controlenglish1361006.67,799N/AAug 6, 2026
visionenglish137981.57,799N/AAug 6, 2026
text style controlpolish1821312.8284N/AAug 6, 2026
textpolish1921258.1284N/AAug 6, 2026
text style controljapanese2031195.61,753N/AAug 6, 2026
textjapanese2111131.61,753N/AAug 6, 2026
text style controlfrench2111300.51,824N/AAug 6, 2026
text style controlkorean2131223.02,059N/AAug 6, 2026
text style controlgerman2171273.13,097N/AAug 6, 2026
textfrench2201227.71,824N/AAug 6, 2026
textspanish2271203.61,448N/AAug 6, 2026
text style controlspanish2271264.51,448N/AAug 6, 2026
textkorean2281127.92,059N/AAug 6, 2026
textgerman2301203.63,097N/AAug 6, 2026
text style controlrussian2501283.710,794N/AAug 6, 2026
text style controlexpert2551270.75,614N/AAug 6, 2026
text style controlindustry medicine and healthcare2561297.65,941N/AAug 6, 2026
text style controlindustry legal and government2611303.26,062N/AAug 6, 2026
text style controlmulti turn2611277.417,062N/AAug 6, 2026
text style controlnon english2611267.548,314N/AAug 6, 2026
textrussian2621225.810,794N/AAug 6, 2026
text style controlcoding2621317.718,888N/AAug 6, 2026
textmulti turn2651226.917,062N/AAug 6, 2026
text style controlindustry mathematical2651260.712,413N/AAug 6, 2026
text style controlmath2661253.413,766N/AAug 6, 2026
textexpert2671171.75,614N/AAug 6, 2026
text style controlindustry software and it services2681306.831,448N/AAug 6, 2026
text style controlindustry writing and literature and language2681268.727,297N/AAug 6, 2026
text style controlinstruction following2681267.238,802N/AAug 6, 2026
text style controlchinese2691275.715,648N/AAug 6, 2026
text style controllonger query2691285.911,870N/AAug 6, 2026
textindustry mathematical2701213.012,413N/AAug 6, 2026
text style controlindustry life and physical and social science2701298.919,089N/AAug 6, 2026
text style controloverall2711280.8109,284N/AAug 6, 2026
text style controlcreative writing2711245.315,592N/AAug 6, 2026
text style controlexclude ties2711199.473,557N/AAug 6, 2026
textindustry medicine and healthcare2721187.55,941N/AAug 6, 2026
text style controlhard prompts2721281.830,725N/AAug 6, 2026
textmath2731213.413,766N/AAug 6, 2026
textnon english2741204.948,314N/AAug 6, 2026
textcoding2751223.218,888N/AAug 6, 2026
text style controlenglish2751288.360,970N/AAug 6, 2026
text style controlhard prompts english2751285.919,193N/AAug 6, 2026
text style controlindustry business and management and financial operations2751261.111,853N/AAug 6, 2026
text style controlindustry entertainment and sports and media2761239.015,961N/AAug 6, 2026
textindustry writing and literature and language2771217.727,297N/AAug 6, 2026
textchinese2781187.715,648N/AAug 6, 2026
textindustry software and it services2781221.931,448N/AAug 6, 2026
textinstruction following2781199.838,802N/AAug 6, 2026
textindustry legal and government2791213.96,062N/AAug 6, 2026
textlonger query2791211.311,870N/AAug 6, 2026
textoverall2801218.2109,284N/AAug 6, 2026
textexclude ties2801108.873,557N/AAug 6, 2026
texthard prompts2811197.430,725N/AAug 6, 2026
textenglish2821226.360,970N/AAug 6, 2026
textcreative writing2841186.515,592N/AAug 6, 2026
texthard prompts english2841204.319,193N/AAug 6, 2026
textindustry entertainment and sports and media2841171.915,961N/AAug 6, 2026
textindustry life and physical and social science2841209.619,089N/AAug 6, 2026
textindustry business and management and financial operations2871173.811,853N/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 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 3 SonnetFeb 29, 202440.0N/A200K200KNoProprietary

What is Claude Sonnet 3?

A concise description based on the published model registry.

Claude 3 Sonnet strikes the ideal balance between intelligence and speed—particularly for enterprise workloads. It delivers strong performance at a lower cost compared to its peers, and is engineered for high endurance in large-scale AI deployments.

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 vs nearby models

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

Claude Sonnet 3vsQwen3 VL 30B A3B ThinkingClaude Sonnet 3vsQwen3 MaxClaude Sonnet 3vsHermes 3 70BClaude Sonnet 3vsQwen3 30B A3BClaude Sonnet 3vsGemma 3 12BClaude Sonnet 3vsJamba 1.5 Large

Models similar to Claude Sonnet 3

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

#110+1.2
AN

Claude Haiku 3.5

Anthropic

41.2 LLMBoard

DetailsCompare
#129-5.8
AN

Claude Haiku 3

Anthropic

34.1 LLMBoard

DetailsCompare
#55+18.9
AN

Claude Opus 3

Anthropic

58.8 LLMBoard

DetailsCompare
#41+23.6
AN

Claude Sonnet 3.7

Anthropic

63.6 LLMBoard

DetailsCompare
#33+29.3
AN

Claude Opus 4.6

Anthropic

69.2 LLMBoard

DetailsCompare
#22+33.5
AN

Claude Sonnet 3.5

Anthropic

73.4 LLMBoard

DetailsCompare

FAQ

Common questions about Claude Sonnet 3.

When was Claude Sonnet 3 released?

Claude Sonnet 3's default version was released on Feb 29, 2024.

How much does Claude Sonnet 3 cost?

No official standard PAYG price is currently available for Claude Sonnet 3.

Who created Claude Sonnet 3?

Claude Sonnet 3 is published under Anthropic in the model registry.

What is the context window for Claude Sonnet 3?

The default version has a 200K token context window.

Is Claude Sonnet 3 open weight?

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

How many API providers offer Claude Sonnet 3?

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

What models should I compare Claude Sonnet 3 with?

Nearby ranked alternatives include Qwen3 VL 30B A3B Thinking, Qwen3 Max, Hermes 3 70B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai