InfoVQA
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
9rows
scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Score, Normalized Score
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Qwen2.5 VL 32B Instruct | 0.83 | — | Self-reported | 2026-05-06 |
| 2 | Qwen2.5 VL 7B Instruct | 0.83 | — | Self-reported | 2026-05-06 |
| 3 | DeepSeek VL2 | 0.78 | — | Self-reported | 2026-05-06 |
| 4 | DeepSeek VL2 Small | 0.76 | — | Self-reported | 2026-05-06 |
| 5 | Phi-4-multimodal-instruct | 0.73 | — | Self-reported | 2026-05-06 |
| 6 | Gemma 3 27B | 0.71 |  Gemma 3 27B google-gemma-3-27b-it | Self-reported | 2026-05-06 |
| 7 | DeepSeek VL2 Tiny | 0.66 | — | Self-reported | 2026-05-06 |
| 8 | Gemma 3 12B | 0.65 | Gemma 3 12B google-gemma-3-12b-it | Self-reported | 2026-05-06 |
| 9 | Gemma 3 4B | 0.50 | Gemma 3 4B google-gemma-3-4b-it | Self-reported | 2026-05-06 |
No matching rows.