Home/Models/Claude 3 Haiku
Anthropic logo

Claude 3 Haiku

by Anthropic · Released Mar 2024

Multimodal
29.8
avg score
Rank #180
Compare
Better than 23% of all models
Context
200K tokens (~100 books)
Input $/1M
$0.25
Output $/1M
$1.25
Type
multimodal
License
Proprietary
Benchmarks
8 tested
Data updated today
About

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) #multimodal

Tested on 8 benchmarks with 28.7% average. Top scores: MMLU (65.1%), ScienceQA (62.7%), Winogrande (48.4%).

Looking for similar performance at lower cost?
Llama 3.3 70B Instruct (free) scores 29.6 (99% as good) at $0.00/1M input · 100% cheaper
Capabilities
coding
10.9
#136 globally
math
8.3
#191 globally
knowledge
47.8
#113 globally
Benchmark Scores
Compare All
Tested on 8 benchmarks · Ranked across 3 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
CadEval

Computer-aided design evaluation. Tests understanding of CAD concepts, 3D modeling, and engineering design principles.

12.0
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

9.8
MATH level 5

Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.

14.9
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

1.7
MMLU

Massive Multitask Language Understanding. 57 subjects from STEM, humanities, and social sciences. The most widely-cited knowledge benchmark.

65.1
ScienceQA

Science questions with multimodal context including diagrams and charts from K-12 curriculum.

62.7
Winogrande

Commonsense coreference resolution. Tests understanding of pronoun references in ambiguous sentences.

48.4
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
claude-3-haiku
Specifications
  • Typemultimodal
  • Context200K tokens (~100 books)
  • ReleasedMar 2024
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.002
Available On
Anthropic logoAnthropic$0.25
Share & Export
Tweet
Claude 3 Haiku is a proprietary multimodal AI model by Anthropic, released in March 2024. It has an average benchmark score of 29.8. Context window: 200K tokens.