model-bench

SKILLWorkflowcommunity
v0.0.0nateslabachMITUpdated 7d agoSource →

Run a 3-leg evaluation against a newly released LLM. Leg 1 is trap questions with deterministic answers, leg 2 is an agentic orchestration task with a planted failure, leg 3 is a brownfield feature build in a real repo. Use when the user wants to vibe-check, test, evaluate, or compare a new frontier

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
6Repo stars
1Clients
1Formats
7d agoLast update
Skill
Authornateslabach
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

Run a 3-leg evaluation against a newly released LLM. Leg 1 is trap questions with deterministic answers, leg 2 is an agentic orchestration task with a planted failure, leg 3 is a brownfield feature build in a real repo. Use when the user wants to vibe-check, test, evaluate, or compare a new frontier model, or mentions model-bench, model vibe check, or launch-day protocol.

Keywords
skillclaude