Hugging Face's logo
AgentNativeResearchLab 's Collections
ALE-Bench CLI-agent trajectories
ARC-AGI-3 · Phase 1: ARA world-model full records
ARC-AGI-3 · Phase 2: truncated-ARA evaluations
DiscoverPhysics · Agent-Native Research Artifacts
LHTB · agent trajectories
FM Open Problems · agent trajectories

LHTB · agent trajectories

Live Hard Task Bench trajectories, one repo per model.