Models

25 current models from 13 labs, ranked by composite score. Verified November 5, 2026.

Sort

25 of 25 models · tap a model for details

Index score and cost per task come from the Artificial Analysis Intelligence Index v5, at each model's best reasoning setting (shown under the score). A dash means the model is not on the index.

Price is list API price per million tokens, input / output. Open weights means the model can be downloaded; it does not always mean an open-source licence, so check the licence note before commercial use.