Not sure which one to pick?
For most tasks, we recommend Claude 4 Sonnet or GPT-5. Both are capable general-purpose models with different response styles.
GPT-5 is a set of models with configurable reasoning and verbosity, find these settings by selecting GPT-5 from the model selector, then clicking on the settings icon next to the model selector.
Click the lightning icon in the text field for a quick response when GPT-5 is selected, when minimal reasoning setting is sufficient. The fast reply setting is also applied when using the enter key to send a mesage with GPT-5.
We recommend using GPT-5 when attaching documents, since GPT-5 has the best and most recent file-input support (including support for images, and perceptual understanding of PDFs).
For particularly complex tasks, Claude 4 Opus offers higher reasoning capabilities than Claude 4 Sonnet.
o3 is a (legacy) reasoning model, that is, it outputs thinking tokens before answering, that performs well on math, science and coding problems. GPT-5 is also a reasoning model, and when used with the high reasoning setting is often more capable than o3 according to benchmarks.
Gemini 2.0 Flash is a fast model from Google Deepmind that can run code.
GPT-4o is the previous generation of OpenAI's GPT models and GPT-4o mini is a faster, less capable alternative.