docs(oss): add note about older models

Author: eyurtsev

src/oss/deepagents/models.mdx

@@ -103,6 +103,10 @@ These models perform well on the Deep Agents eval suite, which tests basic agent
 - **Open-weight models** (available via [Baseten](/oss/integrations/providers/baseten) and [Fireworks](/oss/integrations/providers/fireworks)): GLM-5, Kimi-K2.5, MiniMax-M2.5
 - **Other open-weight models**: Qwen3.5-397B-A17B, Devstral-2-123B
 
+<Note>
+  Older models from these providers (e.g., GPT-4, Claude 3, Gemini 1.5) tend to perform worse on agentic tasks and are not recommended unless you've benchmarked them for your specific use case.
+</Note>
+
 ## Learn more
 
 - [Models in LangChain](/oss/langchain/models): chat model features including tool calling, structured output, and multimodality