Compare to
Overview
Claude 3 Haiku was released almost 1 year after GPT-4.
Claude 3 Haiku
GPT-4
Provider
The entity that provides this model.
Anthropic
OpenAI
Input Context Window
The number of tokens supported by the input context window.
200K
tokens
8,192
tokens
Maximum Output Tokens
The number of tokens that can be generated by the model in a single request.
4,096
tokens
8,192
tokens
Release Date
When the model was first released.
2024-03-13
2023-03-14
Knowledge Cutoff
Limit on the knowledge base used by the model.
August 2023
September 2021
Open Source
API Providers
The providers that offer this model. (This is not an exhaustive list.)
Pricing
Claude 3 Haiku is roughly 120x cheaper compared to GPT-4 for input tokens and roughly 48x cheaper for output tokens.
Claude 3 Haiku
GPT-4
Input
Cost of input data provided to the model.
$0.25
per million tokens
$30.00
per million tokens
Output
Cost of output tokens generated by the model.
$1.25
per million tokens
$60.00
per million tokens
Benchmarks
Compare relevant benchmarks between Claude 3 Haiku and GPT-4.
Claude 3 Haiku
GPT-4
MMLU
Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.
76.7
(5-shot CoT)
86.4
(5-shot)
MMMU
A wide ranging multi-discipline and multimodal benchmark.
50.2
34.9
HellaSwag
A challenging sentence completion benchmark.
85.9
(10-shot)
95.3
(10-shot)
GSM8K
Grade-school math problems benchmark.
Benchmark not available.
92.0
(5-shot)
HumanEval
A benchmark to measure functional correctness for synthesizing programs from docstrings.
Benchmark not available.
67.0
(0-shot)
MATH
Benchmark performance on Math problems ranging across 5 levels of difficulty and 7 sub-disciplines.
Benchmark not available.
Benchmark not available.
Measure & Improve LLM Product Performance.
Get Started