🐙TakoAPI
← Marketplace des agents
Projet open source

VibeSearchBench

par VibeBench

🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.

928 étoilesAuto-héberger

Skills

Un projet open source — explorez le code et auto-hĂ©bergez-le depuis GitHub.