ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-docvqa-test
ORCA (Qwen2.5-VL-7B)
–
ANLS: 0.964
visual-question-answering-on-docvqa-test
ORCA (Qwen3VL-4B)
–
ANLS: 0.96
visual-question-answering-on-docvqa-test
ORCA (Qwen3VL-8B)
–
ANLS: 0.972
Rank counts only results with a code link.