Benchmark
MTVQA Benchmark
What is MTVQA?
MTVQA (Multilingual Text-Centric Visual Question Answering) is the first benchmark featuring high-quality human expert annotations across 9 diverse languages…
- Released
- 2024-05-20
- Modality
- multimodal
- Evaluates
- multimodal, text-to-image, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/mtvqa?top_n=500
MTVQA results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen2-VL-72B-Instruct | Qwen | 0.309 | 2024-08-29 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.