Artificial Analysis ranks Keenable Search 1.0 first on its search index

AIArtificial Analysis reports that Keenable takes 15.0 seconds in realtime mode and 15.5 seconds in pro mode per search task, placing second and third fastest behind Octen's 14.6 seconds, against a board median of about 28 seconds. Search accounts for only 2.3 and 3.0 seconds of that time, with the remainder being model time. Artificial Analysis says both Keenable modes sit on the frontier of its Search Index vs. Time per Task chart, with no product scoring higher in less time.

AIArtificial Analysis says Keenable (pro) sits on the cost frontier of its Search Index vs. Cost per Task chart, with no product scoring higher for less. Keenable costs about $0.040 per task, with search about $0.032 (8 searches at $4 per 1k) and the model about $0.008. Exa (lite, dynamic highlights) costs about the same and scores 79.

AIArtificial Analysis ranks Keenable Search 1.0 first and second on its Search Index, with pro scoring 83 and realtime 82, ahead of Exa and Perplexity at 80. Both modes lead on DeepSearchQA at 88 F1 and cost about $0.040 per task at $4 per 1k searches, over a third below the board median. Realtime and pro return results in 15.0 and 15.5 seconds per task, placing second and third among the products measured.