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 7, 2026
Published models12
Registry coverage12
MetricScore
EvidenceB
InfoVQAtest leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MA | 92.6% | 100.0% | 12 | C | |
| 2 | AC | 89.5% | 90.9% | 12 | C | |
| 3 | AC | 89.2% | 81.8% | 12 | C | |
| 4 | AC | 89.2% | 72.7% | 12 | C | |
| 5 | AC | 87.0% | 63.6% | 12 | C | |
| 6 | AC | 86.0% | 54.5% | 12 | C | |
| 7 | AC | 86.0% | 45.5% | 12 | C | |
| 8 | AC | 84.5% | 36.4% | 12 | C | |
| 9 | 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 |
Score distribution
Top published rows on the benchmark's original scale.
InfoVQAtest highlights
The top published results on this benchmark's own scale.
What is InfoVQAtest?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- InfoVQAtest
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- infovqatest|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.