
Daily AI benchmarks and community votes on model quality
nerfWatch() tests AI models daily through their APIs, against each model's first week of tracking. See scores beside community votes, get alerts for declines and recoveries, and inspect the open-source engine. API tests, not chat-app tests.
nerfWatch() provides daily benchmarking of AI models through API tests, comparing performance against initial tracking data. It features community voting on model quality, alerts for performance changes, and access to the open-source engine.
A source that found nothing is a measurement. A source that has not run is a gap. Neither means the launch lacks the thing.