Claude 3 Opus, developed by Anthropic, features a context window of 200,000 tokens. The model costs 1.5 cents per thousand tokens for input and 7.5 cents per thousand tokens for output. It was released on March 4, 2024, and has achieved impressive scores in benchmarks like HellaSwag with a score of 95.4 in a 10-shot scenario, MMLU with a score of 88.2 in a 5-shot CoT scenario, and MMMU with a score of 59.4.
Overview
Claude 3 Opus
|
|
|---|---|
|
Provider
The entity that provides this model.
|
Anthropic
|
|
Input Context Window
The number of tokens supported by the input context window.
|
200K
tokens
|
|
Maximum Output Tokens
The number of tokens that can be generated by the model in a single request.
|
4,096
tokens
|
|
Open Source
Whether the model's code is available for public use.
|
No
|
|
Release Date
When the model was first released.
|
2024-03-04
|
|
Knowledge Cut-off Date
When the model's knowledge was last updated.
|
|
|
API Providers
The providers that offer this model. (This is not an exhaustive list.)
|
|
|
Empirical Throughput
The number of tokens the model can generate per second.
|
|
Pricing
|
Claude 3 Opus
|
|
|---|---|
|
Input
Cost of input data provided to the model.
|
$15.00
per million tokens
|
|
Output
Cost of output tokens generated by the model.
|
$75.00
per million tokens
|
Benchmarks
|
Claude 3 Opus
|
|
|---|---|
|
MMLU
Evaluating LLM knowledge acquisition in zero-shot and few-shot settings.
|
88.2
(5-shot CoT)
|
|
MMMU
A wide ranging multi-discipline and multimodal benchmark.
|
59.4
|
|
HellaSwag
A challenging sentence completion benchmark.
|
95.4
(10-shot)
|
|
HumanEval
A benchmark to measure functional correctness for synthesizing programs from docstrings.
|
Benchmark not available.
|
|
MATH
Benchmark performance on Math problems ranging across 5 levels of difficulty and 7 sub-disciplines.
|
Benchmark not available.
|
Measure & Improve LLM
Product Performance.
Get Started
© 2023-2024 Context