multimodal benchmark
SimpleVQA
SimpleVQA is a visual question answering benchmark focused on simple queries.
Updated Aug 7, 2026
Published models13
Registry coverage13
MetricScore
EvidenceB
SimpleVQA leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 0.817 points | 100.0% | 13 | C | |
| 2 | ZA | 0.782 points | 91.7% | 13 | C | |
| 3 | BY | 0.745 points | 83.3% | 13 | C | |
| 4 | ME | 0.713 points | 75.0% | 13 | C | |
| 5 | MA | 0.712 points | 66.7% | 13 | C | |
| 6 | BY | 0.711 points | 58.3% | 13 | C | |
| 7 | AC | 0.673 points | 50.0% | 13 | C | |
| 8 | AC | 0.617 points | 41.7% | 13 | C | |
| 9 | AC | 0.613 points | 33.3% | 13 | C | |
| 10 | AC | 0.589 points | 25.0% | 13 | C | |
| 11 | AC | 0.583 points | 16.7% | 13 | C | |
| 12 | AC | 0.561 points | 8.3% | 13 | C | |
| 13 | AC | 0.56 points | 0.0% | 13 | C |
Score distribution
Top published rows on the benchmark's original scale.
SimpleVQA highlights
The top published results on this benchmark's own scale.
What is SimpleVQA?
Definition and scoring fields from the benchmark registry.
SimpleVQA is a visual question answering benchmark focused on simple queries.
Scores are shown in points. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- SimpleVQA
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- simplevqa|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about SimpleVQA.
Which model scores highest on SimpleVQA?
Qwen3.7-Plus is currently ranked first with 0.817 points.
What does SimpleVQA measure?
SimpleVQA is a visual question answering benchmark focused on simple queries.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
13 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.