List your company

Text-to-Image on GenEval 11 (test)

100Accuracy (Single Obj)SD 3.5 M
98.9699.2399.599.77Nov 25, 2025

Evaluation results

MethodLinks
SD 3.5 MBackbone=SD 3.5 M, Reward=None2025.11100865582236268
Individual Expert (Flow-GRPO)Backbone=SD 3.5 M, Reward=GenEval [11]2025.11100969391938493
Individual Expert (Flow-GRPO)Backbone=SD 3.5 M, Reward=PickScore [15]2025.11100947688365976
Individual Expert (Flow-GRPO)Backbone=SD 3.5 M, Reward=OCR [6]2025.11100875682255968
Rewarded SoupBackbone=SD 3.5 M, Reward=[11] + [15] + [6]2025.11100947686437279
MORL-DBackbone=SD 3.5 M, Reward=[11] + [15] + [6]2025.11100999489887891
MORL-DRBackbone=SD 3.5 M, Reward=[11] + [15] + [6]2025.11100826181215967
MapReduce LoRABackbone=SD 3.5 M, Reward=[11] + [15] + [6]2025.11100989388817890
MapReduce LoRA + RaTEBackbone=SD 3.5 M, Reward=[11] + [15] + [6]2025.11100989390957992
Individual Expert (Flow-GRPO)Backbone=FLUX.1-dev, Reward=GenEval [11]2025.111001009089907390
Individual Expert (Flow-GRPO)Backbone=FLUX.1-dev, Reward=PickScore [15]2025.11100956185245770
Individual Expert (Flow-GRPO)Backbone=FLUX.1-dev, Reward=OCR [6]2025.11100847683204668
MORL-DBackbone=FLUX.1-dev, Reward=[11] + [15] + [6]2025.11100998990787388
MORL-DRBackbone=FLUX.1-dev, Reward=[11] + [15] + [6]2025.11100959094737988
MapReduce LoRABackbone=FLUX.1-dev, Reward=[11] + [15] + [6]2025.11100968888817989
SD 3 MBackbone=SD 3 M, Reward=None2025.1199845684325268
SD 3 M + CaPOBackbone=SD 3 M, Reward=VQAScore [21] + MPS [43] + VILA [14]2025.1199876386315971
FLUX.1-devBackbone=FLUX.1-dev, Reward=None2025.1199877182184467
Rewarded SoupBackbone=FLUX.1-dev, Reward=[11] + [15] + [6]2025.1199968188316677