9 tagged benchmarks, measured the same way as everything else here.
davidhariri/artificial-analysis-mcp
MCP server Claude CodeCodexCursor +2
MCP server "artificial-analysis" as configured in davidhariri/artificial-analysis-mcp. Runs dist/index.js with node. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Honest token economics for MCP agents. 68% tokens saved, zero-ML Rust binary. Runs locally from the mcp-sophon npm package.
MCP server Claude CodeCodexCursor +2
DNA-inspired memory layer for AI agents: zero-LLM-call ingestion, retrieval that beats full-context on overflowing histories. Runs locally from the genome-memory Python package.
MCP server Claude CodeCodexCursor +2
Real-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources. Runs locally from the llm-advisor-mcp npm package.
rctruta/sql-benchmarks-dagster
MCP server Claude CodeCodexCursor +2
MCP server "sqlbench" as configured in rctruta/sql-benchmarks-dagster. Runs mcp_server.py with python.
rctruta/sql-benchmarks-dagster
MCP server Claude CodeCodexCursor +2
A reproducible, content-addressed SQL engine benchmarking laboratory. Runs locally from the sqlbenchdag Python package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor
Route AI agent tasks to the best MCP server and LLM, scored on 132+ real benchmark executions. Runs locally from the @toolroute/sdk npm package.
MCP server Claude CodeCodexCursor
CLI + MCP server for OpenRouter models: prices, benchmarks, context and comparisons. Runs locally from the @aggc/or-info npm package.
MCP server Claude CodeCodexCursor +2
MCP server "agmind-mcp" as configured in botAGI/agmind-mcp. Runs locally from the agmind-mcp npm package.