Labsco
MCP SERVER

hvilkenAI

by erorund ↗

A daily benchmark of AI models on Norwegian, Swedish and Danish — rankings with scores, pricing and speed, plus a recommendation for your use case and budget.

LLM Evaluation & Observability
Summary
Which model actually handles Norwegian, measured this week.

General leaderboards say very little about Nordic languages, and a model's standing there moves with each release. Daily testing with a price and a speed column turns "which model" into a question with a current answer.

What it is

An MCP server over hvilkenAI, a benchmark that tests a rotating set of models every day on practical Scandinavian language tasks, drawn from the model pool available through OpenRouter.

What you get
  • Today's rankings for Norwegian, Swedish or Danish with scores, pricing and speed
  • Rankings filtered by tier: premium, midrange or budget
  • One model's daily scores, and its trend across a window of days you choose
  • Models ranked for agent orchestration, combining language quality with instruction-following
  • A recommendation by use case — writing, coding, research, agent or general — and by budget
  • A weekly summary with trends and reliability analysis
Requirements

Access is tiered. The free tier returns yesterday's top three and caps model history at 3 days; Pro returns today's full list and top-three recommendations with full detail.

Setup effort

One command — claude mcp add --transport http hvilkenai https://mcp.hvilkenai.no/mcp