List your company
ResearchFormerly WizWand

Visual Question Answering on ChartQA (val)

81.9Accuracyjina-vlm
1.435222.325143.21564.1049Mar 19, 2022Oct 30, 2022Jun 13, 2023Jan 25, 2024Sep 7, 2024Apr 21, 2025Dec 3, 2025
Updated 8mo ago

Evaluation results

MethodLinks
jina-vlm2025.1281.9
InternVL3.5-2BParameter Count=2B2025.1280.7
InternVL3-2BParameter Count=2B2025.1280.2
Qwen3-VL-2BParameter Count=2B2025.1277.2
Qwen2-VL-2BParameter Count=2B2025.1273.5
DeepStack-HD+LLM=Vicuna-13B, Visual Tokens=14400, Context Length=2880, Pre-training=748K, Instruction-tuning=748K2024.0664
LLaVA-NextLLM=Vicuna-13B, Visual Tokens=2880, Context Length=2880, Pre-training=558K, Instruction-tuning=765K2024.0662.2
VisionTaPasData Table Setting=Gold Data Table Provided2022.0359.32
T5Data Table Setting=Gold Data Table Provided2022.0359.11
VL-T5Data Table Setting=Gold Data Table Provided2022.0358.8
DeepStack-HD+LLM=Vicuna-7B, Visual Tokens=14400, Context Length=2880, Pre-training=558K, Instruction-tuning=748K2024.0656.3
LLaVA-NextLLM=Vicuna-7B, Visual Tokens=2880, Context Length=2880, Pre-training=558K, Instruction-tuning=765K2024.0654.8
TaPasData Table Setting=Gold Data Table Provided2022.0349.16
VisionTaPasData Table Setting=Gold Data Table Not Provided2022.0342.6
T5Data Table Setting=Gold Data Table Not Provided2022.0340.15
TaPasData Table Setting=Gold Data Table Not Provided2022.0339.68
VL-T5Data Table Setting=Gold Data Table Not Provided2022.0338.43
PlotQA*Data Table Setting=Gold Data Table Not Provided2022.0336.15
DeepStack-LLLM=Vicuna-13B, Visual Tokens=2880, Context Length=576, Pre-training=558K, Instruction-tuning=665K2024.0621.2
DeepStack-LLLM=Vicuna-7B, Visual Tokens=2880, Context Length=576, Pre-training=558K, Instruction-tuning=665K2024.0621
DeepStack-VLLM=Vicuna-7B, Visual Tokens=2880, Context Length=576, Pre-training=558K, Instruction-tuning=665K2024.0620.6
DeepStack-VLLM=Vicuna-13B, Visual Tokens=2880, Context Length=576, Pre-training=558K, Instruction-tuning=665K2024.0620.2
LLaVA-1.5LLM=Vicuna-7B, Visual Tokens=576, Context Length=576, Pre-training=558K, Instruction-tuning=665K2024.0618.2
LLaVA-1.5LLM=Vicuna-13B, Visual Tokens=576, Context Length=576, Pre-training=558K, Instruction-tuning=665K2024.0618.2
PREFILData Table Setting=Gold Data Table Not Provided2022.034.53