List your company

Multimodal Understanding on LLaVA-NeXT Multimodal Understanding Suite

83ChartQA AccuracyGenLIP
74.88876.99479.181.206May 1, 2026

Evaluation results

MethodLinks
GenLIPPatches=729, Arch=So/16, Data=8.0B2026.058376.969.664.750.479.178.154.580.189.465.153.270.3
RICE-ViTPatches=729, Arch=L/14, Data=13.0B2026.0582.675.166.258.849.576.577.654.17989.162.951.268.6
GenLIPPatches=576, Arch=So/16, Data=8.0B2026.0579.375.268.559.748.478.677.748.678.289.265.953.168.5
RICE-ViTPatches=576, Arch=L/14, Data=13.0B2026.0579.272.365.957.548.977.976.654.680.788.563.151.868.1
SigLIPv2Patches=729, Arch=So/14, Data=40.0B2026.0579.170.266.258.748.67777.146.680.489.363.452.867.5
AIMv2Patches=576, Arch=L/14, Data=12.8B2026.0577.272.765.957.247.375.478.648.37588.462.250.266.5
SigLIPPatches=729, Arch=So/14, Data=40.0B2026.0576.769.364.755.448.476.27746.179.988.863.747.366.1
MLCDPatches=576, Arch=L/14, Data=12.0B2026.0576.567.861.753.148.47776.554.179.988.761.15166.3
CLIPPatches=576, Arch=L-14, Data=12.8B2026.0575.266.562.552.547.473.274.64875.688.863.74964.8