Connects to the hvilkenAI benchmarking service that tests 12+ language models daily on Norwegian, Swedish, and Danish tasks. You get five tools: query today's benchmark results by language and tier, pull weekly summaries with winners and reliability stats, check historical scores for specific models, view combined orchestrator rankings, and get model recommendations based on use case and budget. Tests run daily at 07:30 CET and cover language quality, instruction following, speed, and cost. Reach for this when you need current data on which models actually perform well on Scandinavian languages, especially if you're building customer service bots or content tools for Nordic markets.
claude mcp add --transport http erorund-hvilkenai-mcp https://mcp.hvilkenai.no/mcp