Best LLM for each task
One model is rarely best at everything. Pick the category that matches your work.
Claude Fable 5.1 has the highest Artificial Analysis Coding Index of the models we track — an independent test of writing and fixing real code.
Drafting, editing and tone control for everyday business writing.
Claude Opus 5.5 has the highest Artificial Analysis Intelligence Index of the models we track, which combines ten hard tests of maths, science, coding and reasoning.
Gemini 3.8 Flash produces answers faster than any other model we track, based on Artificial Analysis's measured median output speed.
GPT-6 Luna gives the most benchmark score per dollar: its Intelligence Index divided by its list price beats every other model we track.
Working reliably across very long documents.
Understanding images, charts, screenshots and documents.
GLM-5.3 has the highest Intelligence Index among models whose weights you can download and run yourself.