Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-rich Image Question Answering (Extraction) on TRINS-VQA
Loading...
63.6
Accuracy
Qwen-VL
13.368
26.409
39.45
52.491
Jun 10, 2024
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen-VL
Resolution=448^2
2024.06
63.6
LaRA
Resolution=336^2
2024.06
62.8
LLaVAR (finetuned)
Resolution=336^2, Fine...
2024.06
61.2
mPLUG-Owl2
Resolution=448^2
2024.06
61
LLaVAR w/ OCR
Resolution=336^2, OCR...
2024.06
58.1
LLaVAR
Resolution=336^2
2024.06
51.7
Instruct-BLIP
Resolution=224^2
2024.06
43.9
LLaVA 1.5
Resolution=336^2
2024.06
38.8
LLaVA
Resolution=336^2
2024.06
23.7
Mini-GPTv2
Resolution=224^2
2024.06
15.3
Feedback
Search any
task
Search any
task