multimodal benchmark
MTVQA
MTVQA (Multilingual Text-Centric Visual Question Answering) is the first benchmark featuring high-quality human expert annotations across 9 diverse languages, consisting of 6,778 question-answer pairs across 2,116 images. It addresses visual-textual misalignment problems in multilingual text-centric VQA.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
MTVQA leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 30.9% | 100.0% | 1 | C |
MTVQA highlights
The top published results on this benchmark's own scale.
What is MTVQA?
Definition and scoring fields from the benchmark registry.
MTVQA (Multilingual Text-Centric Visual Question Answering) is the first benchmark featuring high-quality human expert annotations across 9 diverse languages, consisting of 6,778 question-answer pairs across 2,116 images. It addresses visual-textual misalignment problems in multilingual text-centric VQA.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MTVQA
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mtvqa|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MTVQA.
Which model scores highest on MTVQA?
Qwen2-VL-72B-Instruct is currently ranked first with 30.9%.
What does MTVQA measure?
MTVQA (Multilingual Text-Centric Visual Question Answering) is the first benchmark featuring high-quality human expert annotations across 9 diverse languages, consisting of 6,778 question-answer pairs across 2,116 images. It addresses visual-textual misalignment problems in multilingual text-centric VQA.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 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.