Wikibench

DocVQAtest

multimodal

DocVQA is a Visual Question Answering benchmark on document images containing 50,000 questions defined on 12,000+ document images. The benchmark focuses on understanding document structure and content to answer questions about various document types including letters, memos, notes, and reports from the UCSF Industry Documents Library.

Leaderboard

Showing 11 of 11 results

  1. Qwen3 VL 235B A22B Instruct
    97.1%
    i
  2. Qwen3 VL 32B Instruct
    96.9%
    i
  3. Qwen2-VL-72B-Instruct
    96.5%
    i
  4. Qwen3 VL 235B A22B Thinking
    96.5%
    i
  5. Qwen3 VL 32B Thinking
    96.1%
    i
  6. Qwen3 VL 8B Instruct
    96.1%
    i
  7. Qwen3 VL 4B Instruct
    95.3%
    i
  8. Qwen3 VL 8B Thinking
    95.3%
    i
  9. Qwen3 VL 30B A3B Instruct
    95.0%
    i
  10. Qwen3 VL 30B A3B Thinking
    95.0%
    i
  11. Qwen3 VL 4B Thinking
    94.2%
    i