llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsClaude Haiku 3

Anthropic model product

Claude Haiku 3

Claude 3 Haiku is the fastest and most compact model in the Claude 3 family, designed for near-instant responsiveness. It excels at answering simple queries and requests with unmatched speed, making it ideal for seamless AI experiences that mimic human interactions.

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

Compare
LLMBoard score34.1Claude 3 Haiku
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 Haiku
Released
Mar 13, 2024
Knowledge cutoff
Aug 31, 2023
Parameters
N/A
Context window
200K
Max output
4.1K
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 Haiku category scores

Benchmark results

Published benchmark records for the scored version Claude 3 Haiku.

10 rows
Columns

Show columns

BIG-Bench Hard0.7102155.0%CAug 7, 2026
HellaSwag0.9112761.5%CAug 7, 2026
ARC-C0.9123466.7%CAug 7, 2026
DROP0.8183041.4%CAug 7, 2026
MGSM0.8203136.7%CAug 7, 2026
GSM8k0.9294840.4%CAug 7, 2026
HumanEval0.8547629.3%CAug 7, 2026
MATH0.467715.7%CAug 7, 2026
MMLU0.87510025.3%CAug 7, 2026
GPQA0.32162337.3%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

64 rows
Columns

Show columns

vision style controlchinese101974.81,019N/AAug 6, 2026
visionchinese103910.31,019N/AAug 6, 2026
vision style controloverall1341001.013,380N/AAug 6, 2026
visionoverall137950.313,380N/AAug 6, 2026
vision style controlenglish139992.28,449N/AAug 6, 2026
visionenglish142950.08,449N/AAug 6, 2026
text style controlpolish1901297.2264N/AAug 6, 2026
textpolish2031232.2264N/AAug 6, 2026
text style controljapanese2151172.02,063N/AAug 6, 2026
textjapanese2191102.82,063N/AAug 6, 2026
text style controlkorean2191209.12,364N/AAug 6, 2026
text style controlfrench2201275.61,772N/AAug 6, 2026
textfrench2271193.41,772N/AAug 6, 2026
textkorean2291108.72,364N/AAug 6, 2026
text style controlgerman2341246.23,508N/AAug 6, 2026
text style controlspanish2361236.21,704N/AAug 6, 2026
textspanish2391164.91,704N/AAug 6, 2026
textgerman2431173.53,508N/AAug 6, 2026
text style controlrussian2641266.411,956N/AAug 6, 2026
text style controlexpert2681251.06,336N/AAug 6, 2026
text style controlindustry medicine and healthcare2681278.56,385N/AAug 6, 2026
textrussian2731203.311,956N/AAug 6, 2026
text style controlindustry legal and government2741285.16,799N/AAug 6, 2026
text style controlindustry mathematical2751238.413,491N/AAug 6, 2026
text style controlmath2771231.414,983N/AAug 6, 2026
textexpert2791147.16,336N/AAug 6, 2026
text style controlcoding2791300.720,898N/AAug 6, 2026
text style controlmulti turn2801244.019,344N/AAug 6, 2026
text style controlnon english2801245.953,164N/AAug 6, 2026
textindustry mathematical2821187.413,491N/AAug 6, 2026
textindustry medicine and healthcare2821164.46,385N/AAug 6, 2026
textmath2831188.114,983N/AAug 6, 2026
text style controlindustry software and it services2831285.334,258N/AAug 6, 2026
text style controlindustry writing and literature and language2831245.929,876N/AAug 6, 2026
text style controllonger query2831266.013,976N/AAug 6, 2026
textcoding2841199.520,898N/AAug 6, 2026
text style controlchinese2841247.916,707N/AAug 6, 2026
text style controlindustry business and management and financial operations2841248.013,237N/AAug 6, 2026
text style controlindustry entertainment and sports and media2841220.517,134N/AAug 6, 2026
textmulti turn2851189.919,344N/AAug 6, 2026
text style controlexclude ties2851170.777,578N/AAug 6, 2026
text style controlinstruction following2851244.343,031N/AAug 6, 2026
text style controloverall2861261.1117,701N/AAug 6, 2026
text style controlhard prompts2861264.733,698N/AAug 6, 2026
textindustry legal and government2871191.36,799N/AAug 6, 2026
textindustry writing and literature and language2871193.929,876N/AAug 6, 2026
text style controlcreative writing2871215.016,718N/AAug 6, 2026
textchinese2881153.816,707N/AAug 6, 2026
text style controlindustry life and physical and social science2881272.620,565N/AAug 6, 2026
textnon english2891177.353,164N/AAug 6, 2026
text style controlenglish2891270.164,537N/AAug 6, 2026
text style controlhard prompts english2891269.620,673N/AAug 6, 2026
textoverall2901194.9117,701N/AAug 6, 2026
textexclude ties2901075.777,578N/AAug 6, 2026
textindustry business and management and financial operations2911157.313,237N/AAug 6, 2026
textindustry software and it services2911195.034,258N/AAug 6, 2026
textlonger query2911190.713,976N/AAug 6, 2026
textindustry entertainment and sports and media2921152.417,134N/AAug 6, 2026
texthard prompts2931174.333,698N/AAug 6, 2026
textinstruction following2931173.743,031N/AAug 6, 2026
textindustry life and physical and social science2941178.820,565N/AAug 6, 2026
texthard prompts english2951183.220,673N/AAug 6, 2026
textenglish2961206.364,537N/AAug 6, 2026
textcreative writing2971157.716,718N/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
From $0.25 input, $1.25 output per 1M via Helicone
Tracked offerings
2
2 rows
Columns

Show columns

Heliconeclaude-3-haiku-20240307global$0.25$1.25200KAug 7, 2026
OpenRouteranthropic/claude-3-haikuglobal$0.25$1.25200KAug 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 Haiku 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 HaikuMar 13, 202434.1N/A200K4.1KNoProprietary

What is Claude Haiku 3?

A concise description based on the published model registry.

Claude 3 Haiku is the fastest and most compact model in the Claude 3 family, designed for near-instant responsiveness. It excels at answering simple queries and requests with unmatched speed, making it ideal for seamless AI experiences that mimic human interactions.

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 Haiku 3 vs nearby models

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

Claude Haiku 3vsDeepSeek-V3.1Claude Haiku 3vsCommand R+Claude Haiku 3vsMistral Small 3 24BClaude Haiku 3vsQwen3 VL 8B ThinkingClaude Haiku 3vsQwQ 32BClaude Haiku 3vsQwen2.5 7B

Models similar to Claude Haiku 3

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

#114+5.8
AN

Claude Sonnet 3

Anthropic

40.0 LLMBoard

DetailsCompare
#110+7.1
AN

Claude Haiku 3.5

Anthropic

41.2 LLMBoard

DetailsCompare
#55+24.7
AN

Claude Opus 3

Anthropic

58.8 LLMBoard

DetailsCompare
#41+29.5
AN

Claude Sonnet 3.7

Anthropic

63.6 LLMBoard

DetailsCompare
#33+35.1
AN

Claude Opus 4.6

Anthropic

69.2 LLMBoard

DetailsCompare
#22+39.3
AN

Claude Sonnet 3.5

Anthropic

73.4 LLMBoard

DetailsCompare

FAQ

Common questions about Claude Haiku 3.

When was Claude Haiku 3 released?

Claude Haiku 3's default version was released on Mar 13, 2024.

How much does Claude Haiku 3 cost?

No official standard PAYG price is currently available for Claude Haiku 3. The lowest tracked third-party offer starts at $0.25 input and $1.25 output via Helicone.

Who created Claude Haiku 3?

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

What is the context window for Claude Haiku 3?

The default version has a 200K token context window.

Is Claude Haiku 3 open weight?

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

How many API providers offer Claude Haiku 3?

2 published provider offerings are linked to the default version.

What models should I compare Claude Haiku 3 with?

Nearby ranked alternatives include DeepSeek-V3.1, Command R+, Mistral Small 3 24B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai