List your company

Multimodal Understanding on MMStar (Score)

68.33ScoreSGT-BAGEL
23.81835.37446.9358.486May 16, 2026May 17, 2026May 18, 2026May 19, 2026May 20, 2026

Evaluation results

MethodLinks
SGT-BAGELParams=7B+7B‡2026.0568.33
BAGELParams=7B+7B‡2026.0567.46
Qwen2.5-VL-VIFParams=7B, Base model=Qwen-2.5-VL2026.0565.2
UniWorld-v1Params=7B+12B‡2026.0563.9
VanillaVisual Tokens=360, Prefill Time (s)=0.1337, FLOPs (T)=0.9802, GPU Mem. (GB)=15.97, SpeedUp=1.00×2026.0562.9
Qwen2.5-VL-SFTParams=7B, Base model=Qwen-2.5-VL2026.0562.53
Qwen2.5-VLParams=7B, Base model=Qwen-2.5-VL2026.0562.06
Gemini ProParams=-2026.0559.1
mPLUG-Owl3Params=8B2026.0559.1
SGT-Gen2Params=3B+4B‡2026.0557.07
NGMModel=Qwen3-VL-2B2026.0556.2
OmniGen2Params=3B+4B‡2026.0555.07
Qwen3-VL-2BModel=Qwen3-VL-2B2026.0554.67
SPprunerVisual Tokens=80, Prefill Time (s)=0.0618, FLOPs (T)=0.3688, GPU Mem. (GB)=15.74, SpeedUp=2.16×2026.0550.7
DARTVisual Tokens=80, Prefill Time (s)=0.0833, FLOPs (T)=0.3688, GPU Mem. (GB)=15.74, SpeedUp=1.60×2026.0549.7
Janus-ProParams=7B2026.0546.8
LLaVA-1.5-VIFParams=13B, Base model=LLaVA-1.52026.0541.07
LLaVA-1.5-SFTParams=13B, Base model=LLaVA-1.52026.0539.93
HarmonParams=1.5B2026.0538
LLaVA-1.5-VIFParams=7B, Base model=LLaVA-1.52026.0537.07
VISTAParams=7B, Base model=LLaVA-1.52026.0535.91
LLaVA-1.5-SFTParams=7B, Base model=LLaVA-1.52026.0535.53
LLaVA-1.5Params=13B, Base model=LLaVA-1.52026.0533.87
LLaVA-1.5Params=7B, Base model=LLaVA-1.52026.0533
ChameleonParams=7B2026.0528.93
ReCA-HarmonParams=1.5B2026.0525.53