Launching today
Benchmark Radar
A living database to find and trust AI benchmarks
2 followers
A living database to find and trust AI benchmarks
2 followers
Benchmark Radar tracks 44,978+ AI benchmark, eval, dataset, and data-quality records from 40+ public sources, updated daily. Search the catalog, check score histories with their sources attached, and see saturation and adoption trends before you cite or choose an eval. Dashboard, CLI, and downloadable evidence. Open source.
Free
Launch Team
Render Sandboxes: a computer for every agentGive every agent its own machine. Starts in under a second
Promoted
Hi Product Hunt, I am Koutian, a grad researcher at UT Austin. I built Benchmark Radar because choosing an eval meant opening 30 tabs and trusting screenshots of scores. Radar keeps the evidence attached. The paper (arXiv:2609.11115) hit #1 Paper of the Day on Hugging Face. Ask me anything about benchmark coverage, saturation, or the data pipeline.