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

opencode/models

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

OpenCode model ID format

Models are specified using the 'providerID/modelID' format, for example: opencode('anthropic/claude-sonnet-4-5-20250929')

OpenCode model shortcuts for Anthropic Claude

OpenCode exports OpencodeModels with shortcuts: 'claude-opus-4-5' maps to 'anthropic/claude-opus-4-5-20251101', 'claude-sonnet-4-5' maps to 'anthropic/claude-sonnet-4-5-20250929', 'claude-haiku-4-5' maps to 'anthropic/claude-haiku-4-5-20251001'

OpenCode model shortcuts for OpenAI GPT

OpenCode exports OpencodeModels with shortcuts: 'gpt-4o' maps to 'openai/gpt-4o', 'gpt-4o-mini' maps to 'openai/gpt-4o-mini'

OpenCode model shortcuts for Google Gemini

OpenCode exports OpencodeModels with shortcuts: 'gemini-3.1-pro-preview' maps to 'google/gemini-3.1-pro-preview', 'gemini-2.5-pro' maps to 'google/gemini-2.5-pro', 'gemini-2.5-flash' maps to 'google/gemini-2.5-flash', 'gemini-2.0-flash' maps to 'google/gemini-2.0-flash'

Give your agent this brain