List your company

Tool-use and Complex Reasoning on GAIA Level 2

14.24Pass@1OMAC
0.5124.0767.6411.204May 17, 2025

Evaluation results

MethodLinks
OMACOptimization Dimension=Functional, Configuration=Fun-22025.0514.24
OMACOptimization Dimension=Functional, Configuration=Fun-1.62025.0513.74
OMACOptimization Dimension=Functional, Configuration=Fun-1.42025.0513.04
OMACOptimization Dimension=Structural, Configuration=Str-32025.0512.88
OMACOptimization Dimension=Functional, Configuration=Fun-1.12025.0512.14
OMACOptimization Dimension=Functional, Configuration=Fun-1.52025.0511.97
OMACOptimization Dimension=Structural, Configuration=Str-12025.0511.93
OMACOptimization Dimension=Functional, Configuration=Fun-1.32025.0511.73
OMACOptimization Dimension=Functional, Configuration=Fun-1.22025.0510.92
OMACOptimization Dimension=Functional, Configuration=Fun-1.72025.0510.7
OMACOptimization Dimension=Structural, Configuration=Str-22025.0510.16
DyLAN2025.059.82
Aflow2025.058.23
ADAS2025.053.87
AutoGPT2025.051.04