Responsible AI Use Disclaimer: The tools listed are for informational purposes. Users are responsible for adhering to ethical guidelines. Learn more.

Anthropic ProprietaryNov 2024

Claude 3.5 Haiku

Fast + cheap with a huge context — great for RAG and classification.

Intelligence index
58/ 100
vs all models14th pctile
Composite of MMLU, GPQA, MATH & HumanEval
Speed
130tok/s
vs all models68th pctile
Median across providers, steady state
Blended price
$1.60/ 1M tokens
vs all models59th pctile
3:1 input:output blend

At a glance

Context window
200k tokens
Max output
8k tokens
Input price
$0.80 / 1M tokens
Output price
$4.00 / 1M tokens
Time to first token
0.5s
Input modalities
text
Output modalities
text
License
Proprietary
Provider
Anthropic

Benchmark scores

Public scores from each provider; bars compare this model against the leader in each benchmark.

MMLU
General knowledge across 57 subjects
80.0
leader: 91.8
MMLU Pro
Harder MMLU successor with more reasoning
65.0
leader: 80.0
GPQA
Graduate-level science Q&A
41.0
leader: 78.0
MATH
Competition mathematics
69.0
leader: 94.8
HumanEval
Python code generation pass@1
85.0
leader: 95.8
Strengths
  • 200k context cheap
  • Fast
  • Reliable on extraction
Weaknesses
  • Weaker reasoning than Sonnet
Best for
  • RAG
  • Classification
  • Form filling

Claude 3.5 Haiku vs… popular head-to-heads

One-click matchups against the models people compare Claude 3.5 Haiku with most.

Claude 3.5 Haiku — frequently asked questions

Claude 3.5 Haiku is a large language model from Anthropic, released on 4 November 2024. Fast + cheap with a huge context — great for RAG and classification.

Need help choosing between models?

Compare every option in one sortable table — intelligence, speed and price on a single page.