get_daily_benchmarkLABSCO 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
USE CASES
01
Picking a model for Norwegian content
Read today's ranking for Norwegian with scores, pricing and speed.
02
Finding the cheapest model that still handles Danish
Filter to the budget tier, or ask for a recommendation with the budget set.
03
Checking whether a model got worse after an update
Read its daily scores across the last week or month.
04
Choosing the model that will run your agent
Use the orchestrator ranking, which weighs instruction-following alongside language quality.
05
Reviewing the field weekly instead of daily
Read the weekly summary with its trends and reliability analysis.
5 tools
Listed in project docs. Your client may show a different list.
get_model_historyget_orchestrator_rankingget_recommendationget_weekly_summaryBEFORE YOU INSTALL
What to know first
Tools you get
5 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
INSTALLATION
Connect your client
Server setup
claude mcp add
Claude Code
TERMINAL
claude mcp add --transport http hvilkenai https://mcp.hvilkenai.no/mcpHosted endpoint
ENDPOINT URL
https://mcp.hvilkenai.no/mcpAdd this hosted endpoint to your MCP client, then sign in.
MCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"hvilkenai": {
"url": "https://mcp.hvilkenai.no/mcp"
}
}
}VS Code
VS CODE · JSON
{
"servers": {
"hvilkenai": {
"url": "https://mcp.hvilkenai.no/mcp"
}
}
}Other routes
Direct API (curl)
DIRECT API (CURL) · TERMINAL
curl -X POST https://mcp.hvilkenai.no/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
