multimodal benchmark
InfoVQA Leaderboard
InfoVQA is a multimodal dataset with 30,000 questions and 5,000 infographic images requiring joint reasoning over document layout, textual content, graphical elements, data visualizations, elementary reasoning, and arithmetic skills.
Updated Sep 5, 2026
Models10
Model coverage10
MetricScore
EvidenceB
InfoVQA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score83.40% | Percentile100.00% | Participants10 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score82.60% | Percentile88.89% | Participants10 | EvidenceC | Evaluated |
| Rank03 | ModelDE | Score78.10% | Percentile77.78% | Participants10 | EvidenceC | Evaluated |
| Rank04 | ModelDE | Score75.80% | Percentile66.67% | Participants10 | EvidenceC | Evaluated |
| Rank05 | ModelMI | Score72.70% | Percentile55.56% | Participants10 | EvidenceC | Evaluated |
| Rank06 | ModelGO | Score70.60% | Percentile44.44% | Participants10 | EvidenceC | Evaluated |
| Rank07 | ModelDE | Score66.10% | Percentile33.33% | Participants10 | EvidenceC | Evaluated |
| Rank08 | ModelCO | Score65.20% | Percentile22.22% | Participants10 | EvidenceC | Evaluated |
| Rank09 | ModelGO | Score64.90% | Percentile11.11% | Participants10 | EvidenceC | Evaluated |
| Rank10 | ModelGO | Score50.00% | Percentile0.00% | Participants10 | EvidenceC | Evaluated |
InfoVQA Highlights
The leading models and scores on this benchmark.
InfoVQA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for InfoVQA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is InfoVQA?
What InfoVQA measures and how its scores work.
InfoVQA is a multimodal dataset of questions and infographic images.
It measures performance using Score, reported as a ratio, on questions requiring joint reasoning over document layout, textual content, graphical elements, data visualizations, elementary reasoning, and arithmetic skills.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- InfoVQA
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about InfoVQA.
Which model scores highest on InfoVQA?
Qwen2.5 VL 32B Instruct is currently ranked first with 83.40%.
What are the top three models on InfoVQA?
The current leaders are Qwen2.5 VL 32B Instruct (83.40%), Qwen2.5 VL 7B Instruct (82.60%), and DeepSeek VL2 (78.10%).
Which InfoVQA model has the lowest official input price?
Qwen2.5 VL 7B Instruct has the lowest matched official input price at $0.35 input / $1.1 output per 1M tokens.
Which models are fastest among InfoVQA results?
The fastest matched records are Gemma 3 27B (33.00 tok/s via DeepInfra), Gemma 3 12B (33.00 tok/s via DeepInfra), and Gemma 3 4B (33.00 tok/s via DeepInfra).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.