Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
Search 264 AI benchmarks by category, with data sources and licences for each.
Remote server: your requests and data go to aibenchmarkindex.com. Claude Code: claude mcp add --transport http ai-benchmark-index https://aibenchmarkindex.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_listings — Search published benchmarks by text, place and category.get_listing — Get one published benchmark by its slug.list_places — List countries, regions and cities that have benchmarks.list_categories — List categories with their benchmark counts.get_stats — Get the number of published benchmarks, places and categories, and when the data last changed.list_sources — List where the benchmark data comes from, with the license and refresh of each source.list_products — List the affiliate products, with the price each had on the day it was checked. Filter by product category.get_product — Get one affiliate product by its slug, with its page and outbound link.list_product_categories — List the product categories with their product counts.list_courses — List the published academy courses with their level, length, pass mark and certificate validity.get_course — Get one published academy course by its slug, with its objectives, lessons and FAQ. Exam questions and answers are never returned.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.