multimodal benchmark
InfoVQAtest
InfoVQA test set with infographic images requiring joint reasoning over document layout, textual content, graphical elements, and data visualizations with elementary reasoning and arithmetic skills
Updated Aug 11, 2026
Models12
Model coverage12
MetricScore
EvidenceB
InfoVQAtest Ranking
Higher score ranks better on this benchmark.
| 01 | MA | 92.6% | 100.0% | 12 | C | |
| 02 | AC | 89.5% | 90.9% | 12 | C | |
| 03 | AC | 89.2% | 81.8% | 12 | C | |
| 04 | AC | 89.2% | 72.7% | 12 | C | |
| 05 | AC | 87.0% | 63.6% | 12 | C | |
| 06 | AC | 86.0% | 54.5% | 12 | C | |
| 07 | AC | 86.0% | 45.5% | 12 | C | |
| 08 | AC | 84.5% | 36.4% | 12 | C | |
| 09 | AC | 83.1% | 27.3% | 12 | C | |
| 10 | AC | 83.0% | 18.2% | 12 | C | |
| 11 | AC | 82.0% | 9.1% | 12 | C | |
| 12 | AC | 80.3% | 0.0% | 12 | C |
InfoVQAtest Score Distribution
A closer view of the leading scores on this benchmark.
InfoVQAtest Highlights
The leading models and scores on this benchmark.
What is InfoVQAtest?
What InfoVQAtest measures and how its scores work.
InfoVQA test set with infographic images requiring joint reasoning over document layout, textual content, graphical elements, and data visualizations with elementary reasoning and arithmetic skills
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- InfoVQAtest
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- infovqatest|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about InfoVQAtest.
Which model scores highest on InfoVQAtest?
Kimi K2.5 is currently ranked first with 92.6%.
What does InfoVQAtest measure?
InfoVQA test set with infographic images requiring joint reasoning over document layout, textual content, graphical elements, and data visualizations with elementary reasoning and arithmetic skills
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
12 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.