[8.14] [bug] Updates LLM Matrix (#5614)

* Updates LLM Matrix * fixes table * Update docs/serverless/AI-for-security/llm-performance-matrix.mdx Co-authored-by: Nastasha Solomon <[email protected]> --------- Co-authored-by: Nastasha Solomon <[email protected]>
elastic · Jul 26, 2024 · c62809a · c62809a
1 parent 26aee2a
commit c62809a
Show file tree

Hide file tree

Showing 2 changed files with 14 additions and 14 deletions.
diff --git a/docs/AI-for-security/llm-performance-matrix.asciidoc b/docs/AI-for-security/llm-performance-matrix.asciidoc
@@ -3,13 +3,13 @@
 
 This table describes the performance of various large language models (LLMs) for different use cases in {elastic-sec}, based on our internal testing. To learn more about these use cases, refer to <<attack-discovery, Attack discovery>> or <<security-assistant, AI Assistant>>.
 
-[cols="1,1,1,1,1,1,1", options="header"]
+[cols="1,1,1,1,1,1", options="header"]
 |===
-| *Feature*                     | *Model*               |                    |                   |         |              |             
-|                               | *Claude 3: Opus*      | *Claude 3: Sonnet* | *Claude 3: Haiku* | *GPT-4o* | *GPT-4 Turbo*| *GPT-4 32K* 
+| *Feature*                     | *Model*               |                    |                   |         |                          
+|                               | *Claude 3: Opus*      | *Claude 3.5: Sonnet* | *Claude 3: Haiku* | *GPT-4o* | *GPT-4 Turbo* 
 
-| *Assistant - General*         | Excellent             | Excellent          | Excellent         | Excellent | Excellent     | Excellent
-| *Assistant - {esql} Generation*| Great                 | Great              | Poor              | Excellent | Poor          | Excellent
-| *Assistant - Alert Questions* | Excellent             | Excellent          | Excellent         | Excellent | Poor          | Good (limited context)
-| *Attack discovery*            | Excellent             | Great              | Poor              | Poor      | Good          | Good (limited context)
+| *Assistant - General*         | Excellent             | Excellent          | Excellent         | Excellent | Excellent     
+| *Assistant - {esql} Generation*| Great                 | Great              | Poor              | Excellent | Poor          
+| *Assistant - Alert Questions* | Excellent             | Excellent          | Excellent         | Excellent | Poor          
+| *Attack discovery*            | Excellent             | Excellent            | Poor              | Poor      | Good        
 |===
diff --git a/docs/serverless/AI-for-security/llm-performance-matrix.mdx b/docs/serverless/AI-for-security/llm-performance-matrix.mdx
@@ -8,11 +8,11 @@ status: in review
 
 This table describes the performance of various large language models (LLMs) for different use cases in ((elastic-sec)), based on our internal testing. To learn more about these use cases, refer to <DocLink slug="/serverless/security/attack-discovery" text="Attack discovery"/> or <DocLink slug="/serverless/security/ai-assistant" text="AI Assistant"/>.
 
-|           **Feature:**        | **Model**             |                    |                    |            |                 |                |
-|-------------------------------|-----------------------|--------------------|--------------------|------------|-----------------|----------------|
-|                               | **Claude 3: Opus**    | **Claude 3: Sonnet** | **Claude 3: Haiku** | **GPT-4o** | **GPT-4 Turbo** | **GPT-4 32K**  |
-| **Assistant: general**       | Excellent             | Excellent          | Excellent          | Excellent  | Excellent       | Excellent      |
-| **Assistant: ((esql)) generation** | Great           | Great              | Poor               | Excellent  | Poor            | Excellent      |
-| **Assistant: alert questions** | Excellent          | Excellent          | Excellent          | Excellent  | Poor            | Good (limited context) |
-| **Attack discovery**          | Excellent             | Great              | Poor               | Poor       | Good            | Good (limited context) |
+|           **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: ((esql)) generation** | Great            | Great              | Poor               | Excellent  | Poor            | 
+| **Assistant: alert questions** | Excellent            | Excellent          | Excellent          | Excellent  | Poor            |
+| **Attack discovery**          | Excellent             | Excellent          | Poor               | Poor       | Good            |