Keenable AI Open-Sources NEEDLE: A Live Search Benchmark That Rebuilds Its Query Set Every Hour
What changed
Keenable AI has open-sourced NEEDLE, a live benchmark for testing web search APIs. It rebuilds its query set every hour, helping prevent search systems from downloading public answers and bypassing the retrieval test.
What this means for you
Teams evaluating web search tools can use a changing test set that is harder to game through answer-key access. The benchmark is open source, but the feed does not specify its license or setup requirements.
