Using our variety of language models allows you to pick the one that best suits your specific needs, whether it's generating creative content, providing detailed technical explanations, or engaging in casual conversation. This flexibility ensures you get the best performance for your particular task.
You can select the language model for all consultants who have the "Writing" capability by visiting their settings.
<aside> 💡 You can see an agent's capabilities by clicking on their profile image and hovering over the icons beneath their name.
</aside>
To access your agent settings and switch their language model, click the settings icon at the top right of the window. Then, choose the "Writing Model" drop-down menu and select your preferred model.
<aside> 💡 Note: The writing model you choose will only apply to the current conversation. When you initiate a new conversation, the agent will return to using the default GPT-4 model.
</aside>
Let's take a look at a writing sample from each model, all responding to the same prompt, to see how they differ in their reactions.
Olympia operates on the GPT-4 model as its default. GPT-4, an advanced iteration of the Generative Pre-trained Transformer series, boasts enhanced capabilities in natural language understanding and generation.
GPT-4 Turbo is optimised for speed and efficiency, allowing for quicker generation of text while maintaining high-quality results. Note that optimising for speed may sacrifice some level of accuracy or coherence in certain scenarios, and the model may not perform as well on complex or nuanced prompts.
Claude 3 Sonnet is engineered to address the specific needs of businesses that require both swift processing and smart, insightful AI interactions. With a context window of 200,000 tokens, Sonnet is adept at handling extensive data, making it highly versatile across various use cases.
Opus, Claude's most intelligent model, outperforms its peers on most of the common evaluation benchmarks for AI systems, including undergraduate-level expert knowledge (MMLU), graduate level expert reasoning (GPQA), basic mathematics (GSM8K), and more. It exhibits near-human levels of comprehension and fluency on complex tasks, leading the frontier of general intelligence.
