TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Janus-Pro-7B

Janus-Pro-7B

Reported on 6 benchmarks across 6 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

  • Text-to-Image GenerationonGenEval
    Overall· 2025-01-29
    0.8
    best: 0.95 (SD3.5-Medium+Flow-GRPO)
    SOTA
    Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model ScalingarXiv:2501.17811
  • Visual Question Answering (VQA)onMM-Vet
    GPT-4 score· 2025-01-29
    50
    best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
    Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model ScalingarXiv:2501.17811
  • Visual Question AnsweringonMM-Vet
    GPT-4 score· 2025-01-29
    50
    best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
    Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model ScalingarXiv:2501.17811

Audio2 results

  • 10-shot image generationonGenEval
    Overall· 2025-01-29
    0.8
    best: 0.95 (SD3.5-Medium+Flow-GRPO)
    SOTA
    Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model ScalingarXiv:2501.17811
  • 1 Image, 2*2 StitchionGenEval
    Overall· 2025-01-29
    0.8
    best: 0.95 (SD3.5-Medium+Flow-GRPO)
    SOTA
    Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model ScalingarXiv:2501.17811

Medical1 result

  • Image GenerationonGenEval
    Overall· 2025-01-29
    0.8
    best: 0.95 (SD3.5-Medium+Flow-GRPO)
    SOTA
    Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model ScalingarXiv:2501.17811