List your company

Multi-modal Understanding on CV-Bench, BLINK, RealWorldQA, MathVista, MMStar, MMVet Suite

53.8Average ScoreLATTE
41.11244.40647.750.994Dec 7, 2024

Evaluation results

MethodLinks
LATTELanguage / Vision=Qwen2-7B/SigLIP, Starting checkpoint=LLaVA-OV Stage 1.52024.1253.8
Vanilla ITLanguage / Vision=Qwen2-7B/SigLIP, Starting checkpoint=LLaVA-OV Stage 1.52024.1249.5
LATTELanguage / Vision=LLaMA3-8B/SigLIP, Starting checkpoint=Mantis Instruct-tuned2024.1248.2
LATTELanguage / Vision=LLaMA3-8B/CLIP, Starting checkpoint=Mantis Pretrained (Configuration 2)2024.1247.2
LATTELanguage / Vision=LLaMA3-8B/CLIP, Starting checkpoint=Mantis Pretrained2024.1246.7
Vanilla ITLanguage / Vision=LLaMA3-8B/SigLIP, Starting checkpoint=Mantis Instruct-tuned2024.1243.1
Vanilla ITLanguage / Vision=LLaMA3-8B/CLIP, Starting checkpoint=Mantis Pretrained (Configuration 2)2024.1242.1
Vanilla ITLanguage / Vision=LLaMA3-8B/CLIP, Starting checkpoint=Mantis Pretrained2024.1241.6