Nobody has claimed this office yet. Tablif records every new product and gives it an office; when its owner claims it, the lights go on.

What Tablif read on Benchmark Radar's site

Benchmark Radar describes itself as: “Benchmark Radar A living database to find and trust AI benchmarks”

Calls itself “Search Engine” and “database”.

“Search Engine for AI Benchmarks & Evals”

“A living database to find and trust AI benchmarks”

Claims “one place”.

“There was no one place that listed them, said what each one tests, and showed which models had been measured on it.”

Sells to developers. In English.

“Query the whole catalog offline from the command line”

“English”

A command-line tool and web app. Runs locally and works offline. Distributed through the GitHub. Open source. AI is a side feature.

“Dashboard, CLI, and downloadable evidence.”

“Query the whole catalog offline from the command line”

Names Hugging Face, Kit and 1 more on its pages.

“Benchmark Radar tracks 44,978+ AI benchmark, eval, dataset, and data-quality records from 40+ public sources, updated daily.”

“Hugging Face paper upvotes and Hugging Face dataset downloads over the last 30 days.”

Live, no waitlist. Claims “44,978+”. Publishes a blog.

“Benchmark Radar tracks 44,978+ AI benchmark, eval, dataset, and data-quality records from 40+ public sources”

“Blog -> https://benchmark-radar.org/blog/”

Tablif read these pages, last on 6 Nov 2026. Everything above is what the product says about itself; Tablif does not verify every claim.

Benchmark Radar · Office #64,021