Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Large Multi-modal Model Evaluation on LLaVA-Bench Tool Use (test)

0.893Grounding

LLaVA-Plus

0.278360.437930.59750.75707Nov 9, 2023
Updated 3d ago

Evaluation Results

MethodLinks
2023.11
0.8930.9440.9670.4880.823
2023.11
0.8860.8890.9020.3840.765
2023.11
0.7750.9560.9520.3930.769
2023.11
0.560.840.960.4480.702
2023.11
0.4710.8710.770.2360.587
2023.11
0.4170.4850.720.3190.485
2023.11
0.3651.0531.0330.60.763
2023.11
0.3020.9471.0380.7730.765