multimodal benchmark
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 Nov 13, 2026
Higher score ranks better on this benchmark.
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelLA | Score86.20% | Percentile100.00% | Participants11 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score83.40% | Percentile90.00% | Participants11 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score82.60% | Percentile80.00% | Participants11 | EvidenceC | Evaluated |
| Rank04 | ModelDE | Score78.10% | Percentile70.00% | Participants11 | EvidenceC | Evaluated |
| Rank05 | ModelDE | Score75.80% | Percentile60.00% | Participants11 | EvidenceC | Evaluated |
| Rank06 | ModelMI | Score72.70% | Percentile50.00% | Participants11 | EvidenceC | Evaluated |
| Rank07 | ModelGO | Score70.60% | Percentile40.00% | Participants11 | EvidenceC | Evaluated |
| Rank08 | ModelDE | Score66.10% | Percentile30.00% | Participants11 | EvidenceC | Evaluated |
| Rank09 | ModelCO | Score65.20% | Percentile20.00% | Participants11 | EvidenceC | Evaluated |
| Rank10 | ModelGO | Score64.90% | Percentile10.00% | Participants11 | EvidenceC | Evaluated |
| Rank11 | ModelGO | Score50.00% | Percentile0.00% | Participants11 | EvidenceC | Evaluated |
The leading models and scores on this benchmark.
A closer view of the leading scores on this benchmark.
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
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.
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about InfoVQA.
LFM3-VL-2B is currently ranked first with 86.20%.
The current leaders are LFM3-VL-2B (86.20%), Qwen2.5 VL 32B Instruct (83.40%), and Qwen2.5 VL 7B Instruct (82.60%).
No matched official input price is currently available.
The fastest matched records are Gemma 3 4B (33.00 tok/s via DeepInfra) and Phi-4-multimodal-instruct (25.00 tok/s via DeepInfra).
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.
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.
Yes. Higher values rank better for this benchmark.
11 model results are currently shown.
No. This benchmark is shown for reference but does not contribute to the overall score.
Ranking basisThis infovqa AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
LFM3-VL-2B currently leads InfoVQA with 86.20%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.