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

llamagate/models

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

LlamaGate available language models

LlamaGate provides the following language models: llama-3.1-8b (131K context), llama-3.2-3b (131K context), qwen3-8b (32K context), mistral-7b-v0.3 (32K context), deepseek-r1-8b (64K context), deepseek-r1-7b-qwen (131K context), openthinker-7b (32K context), dolphin3-8b (128K context), qwen2.5-coder-7b (32K context), codellama-7b (16K context), qwen3-vl-8b (32K context, vision), llava-7b (4K context, vision), and gemma3-4b (128K context, vision).

LlamaGate available embedding models

LlamaGate provides the following embedding models: nomic-embed-text (8K context), embeddinggemma-300m (2K context), and qwen3-embedding-8b (40K context).

Give your agent this brain