#529·OpenManus

eval on GAIA benchmark

Author: pulkitmehtaworkCreated Mar 12, 2025Updated Aug 17, 2026
Labels:star: top issue

I propose to have eval on GAIA benchmark e.g. OWL by camel.ai has score of 58.18 and 1st among open source agents .https://github.com/camel-ai/owl

Source: FoundationAgents/OpenManus