List your company

Text-based Visual Question Answering on TextVQA (TQA)

66.6ScoreVILA
24.27235.26146.2557.239Feb 15, 2026

Evaluation results

MethodLinks
VILAPretrained-LLM=LLaMA2-7B, Model Category=Understanding Only Model2026.0266.6
LLaVA-1.6(HD)Pretrained-LLM=Vicuna-7B, Model Category=Understanding Only Model2026.0264.9
Emu3-ChatModel Category=Unified Model2026.0264.7
mPLUG-Owl2Pretrained-LLM=LLaMA2-7B, Model Category=Understanding Only Model2026.0258.2
InternVL-ChatPretrained-LLM=Vicuna-7B, Model Category=Understanding Only Model2026.0257
EVE-7B(HD)Pretrained-LLM=Vicuna-7B, Model Category=Unified Model2026.0256.8
TokenFlow-LPretrained-LLM=Vicuna-13B, Model Category=Unified Model2026.0254.1
UniWeTok-ChatPretrained-LLM=Qwen3-8B, Model Category=Unified Model2026.0253.7
UniTokPretrained-LLM=LLaMA-2-7B, Model Category=Unified Model2026.0251.6
InstructBLIPPretrained-LLM=Vicuna-7B, Model Category=Understanding Only Model2026.0250.1
VILA-UPretrained-LLM=LLaMA2-7B, Model Category=Unified Model2026.0248.3
LWM-7BModel Category=Unified Model2026.0247.7
LLaVA-1.5Pretrained-LLM=Vicuna-7B, Model Category=Understanding Only Model2026.0246.1
IDEFICS-9BPretrained-LLM=LLaMA-7B, Model Category=Understanding Only Model2026.0225.9