InfoVQA

multimodal

InfoVQA dataset with 30,000 questions and 5,000 infographic images requiring joint reasoning over document layout, textual content, graphical elements, and data visualizations with elementary reasoning and arithmetic skills

Leaderboard

Showing 9 of 9 results

Qwen2.5 VL 32B Instruct

83.4%

i
Qwen2.5 VL 7B Instruct

82.6%

i
DeepSeek VL2

78.1%

i
DeepSeek VL2 Small

75.8%

i
Phi-4-multimodal-instruct

72.7%

i
Gemma 3 27B

70.6%

i
DeepSeek VL2 Tiny

66.1%

i
Gemma 3 12B

64.9%

i
Gemma 3 4B

50.0%

i