IMPORTANT: No additional bug fixes or documentation updates
will be released for this version. For the latest information, see the
current release documentation.
Large language model performance matrix
edit
IMPORTANT: This documentation is no longer updated. Refer to Elastic's version policy and the latest documentation.
Large language model performance matrix
editThis table describes the performance of various large language models (LLMs) for different use cases in Elastic Security, based on our internal testing. To learn more about these use cases, refer to Attack discovery or AI Assistant.
Feature | Model | ||||
---|---|---|---|---|---|
Claude 3: Opus |
Claude 3.5: Sonnet |
Claude 3: Haiku |
GPT-4o |
GPT-4 Turbo |
|
Assistant - General |
Excellent |
Excellent |
Excellent |
Excellent |
Excellent |
Assistant - ES|QL generation |
Great |
Great |
Poor |
Excellent |
Poor |
Assistant - Alert questions |
Excellent |
Excellent |
Excellent |
Excellent |
Poor |
Attack discovery |
Excellent |
Excellent |
Poor |
Poor |
Good |
Was this helpful?
Thank you for your feedback.