List your company

Vision-Language Evaluation on MME Leaderboard (full)

138.33Existence ScoreHALC
68.993286.9941104.995122.9959May 26, 2025

Evaluation results

MethodLinks
HALCModel=MiniGPT-4, Tokens=128, Samples=1202025.05138.33—————63.3358.3378.33———————
RVCDModel=MiniGPT-4, Tokens=128, Samples=1202025.05130—————51.6653.3370———————
RVCDModel=mPLUG-Owl2, Tokens=128, Samples=1202025.05130—————7053.33125———————
DoLaModel=MiniGPT-4, Tokens=128, Samples=1202025.05128.33—————606078.33———————
VCDModel=mPLUG-Owl2, Tokens=128, Samples=1202025.05126.66—————81.665591.66———————
VCDModel=MiniGPT-4, Tokens=128, Samples=1202025.05125—————53.3351.6665———————
RVCDModel=LLaVA-1.5, Tokens=128, Samples=1202025.05123.33—————606595———————
GreedyModel=mPLUG-Owl2, Tokens=128, Samples=1202025.05111.66—————68.3370120———————
DoLaModel=mPLUG-Owl2, Tokens=128, Samples=1202025.05111.66—————6565120———————
GreedyModel=MiniGPT-4, Tokens=128, Samples=1202025.05108.33—————48.3356.6678.33———————
GreedyModel=LLaVA-1.5, Tokens=128, Samples=1202025.05105—————605065———————
OperaModel=mPLUG-Owl2, Tokens=128, Samples=1202025.05105—————63.335090———————
VCDModel=LLaVA-1.5, Tokens=128, Samples=1202025.05100—————56.666085———————
HALCModel=mPLUG-Owl2, Tokens=128, Samples=1202025.0598.33—————6553.33115———————
OperaModel=LLaVA-1.5, Tokens=128, Samples=1202025.0588.33—————6053.3380———————
DoLaModel=LLaVA-1.5, Tokens=128, Samples=1202025.0575—————53.335560———————
HALCModel=LLaVA-1.5, Tokens=128, Samples=1202025.0573.33—————58.3353.3365———————
OperaModel=MiniGPT-4, Tokens=128, Samples=1202025.0571.66—————46.6656.6653.33———————