new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

apertis/models

3 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Apertis chat model access

Chat models are accessed using apertis('model-id') or apertis.chat('model-id') syntax.

Apertis supported chat models

Apertis supports OpenAI models (gpt-5.2, gpt-5.2-chat, gpt-5.2-pro), Anthropic models (claude-opus-4-5-20251101, claude-sonnet-4.5, claude-haiku-4.5), Google models (gemini-3.1-pro-preview, gemini-3-flash-preview, gemini-2.5-pro), and other models including glm-4.7, minimax-m2.1, plus 470+ additional models.

Apertis text embedding models

Text embedding models are accessed using apertis.textEmbeddingModel('model-id'). Supported embedding models are: text-embedding-3-small, text-embedding-3-large, and text-embedding-ada-002.

Give your agent this brain