Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/MindOmni

MindOmni

Reported on 28 benchmarks across 4 tasks · 1 paper · 20 SOTA

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

Audio14 results

10-shot image generationonGenEval
Color Attri.· 2025-05-19
0.71
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
10-shot image generationonGenEval
Colors· 2025-05-19
0.9
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
10-shot image generationonGenEval
Counting· 2025-05-19
0.71
best: 0.81 (UniWorld-V1 (Rewrite))
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
10-shot image generationonGenEval
Position· 2025-05-19
0.71
best: 0.74 (UniWorld-V1 (Rewrite))
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
10-shot image generationonGenEval
Two Obj.· 2025-05-19
0.94
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
1 Image, 2*2 StitchionGenEval
Color Attri.· 2025-05-19
0.71
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
1 Image, 2*2 StitchionGenEval
Colors· 2025-05-19
0.9
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
1 Image, 2*2 StitchionGenEval
Counting· 2025-05-19
0.71
best: 0.81 (UniWorld-V1 (Rewrite))
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
1 Image, 2*2 StitchionGenEval
Position· 2025-05-19
0.71
best: 0.74 (UniWorld-V1 (Rewrite))
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
1 Image, 2*2 StitchionGenEval
Two Obj.· 2025-05-19
0.94
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
10-shot image generationonGenEval
Overall· 2025-05-19
0.83
best: 0.95 (SD3.5-Medium+Flow-GRPO)
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
10-shot image generationonGenEval
Single Obj.· 2025-05-19
0.99
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
1 Image, 2*2 StitchionGenEval
Overall· 2025-05-19
0.83
best: 0.95 (SD3.5-Medium+Flow-GRPO)
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
1 Image, 2*2 StitchionGenEval
Single Obj.· 2025-05-19
0.99
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031

Medical7 results

Image GenerationonGenEval
Color Attri.· 2025-05-19
0.71
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Image GenerationonGenEval
Colors· 2025-05-19
0.9
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Image GenerationonGenEval
Counting· 2025-05-19
0.71
best: 0.81 (UniWorld-V1 (Rewrite))
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Image GenerationonGenEval
Position· 2025-05-19
0.71
best: 0.74 (UniWorld-V1 (Rewrite))
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Image GenerationonGenEval
Two Obj.· 2025-05-19
0.94
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Image GenerationonGenEval
Overall· 2025-05-19
0.83
best: 0.95 (SD3.5-Medium+Flow-GRPO)
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Image GenerationonGenEval
Single Obj.· 2025-05-19
0.99
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031

Natural Language Processing7 results

Text-to-Image GenerationonGenEval
Color Attri.· 2025-05-19
0.71
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Text-to-Image GenerationonGenEval
Colors· 2025-05-19
0.9
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Text-to-Image GenerationonGenEval
Counting· 2025-05-19
0.71
best: 0.81 (UniWorld-V1 (Rewrite))
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Text-to-Image GenerationonGenEval
Position· 2025-05-19
0.71
best: 0.74 (UniWorld-V1 (Rewrite))
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Text-to-Image GenerationonGenEval
Two Obj.· 2025-05-19
0.94
SOTA
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Text-to-Image GenerationonGenEval
Overall· 2025-05-19
0.83
best: 0.95 (SD3.5-Medium+Flow-GRPO)
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031
Text-to-Image GenerationonGenEval
Single Obj.· 2025-05-19
0.99
MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO arXiv:2505.13031