List your company
ResearchFormerly WizWand

Text-to-Image Generation on GenEval (GenEval Score and R Metric)

87GenEval ScoreBase model
38.43251.04163.6576.259Nov 20, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Base modelModel Context=Qwen-Image, P.(B)↓=20, M.(%)↓=100, L.(ms)↓=26252025.11870
PPCL(14B)Model Context=Qwen-Image, P.(B)↓=14, M.(%)↓=79.4, L.(ms)↓=17922025.1184.70.42
PPCL(Fine-tuning)Model Context=Qwen-Image, P.(B)↓=10, M.(%)↓=66.9, L.(ms)↓=14622025.1182.83.29
PPCL(12B)Model Context=Qwen-Image, P.(B)↓=12, M.(%)↓=71.4, L.(ms)↓=15142025.1180.13.03
PPCL(10B)Model Context=Qwen-Image, P.(B)↓=10, M.(%)↓=66.9, L.(ms)↓=14622025.1178.46.88
HierarchicalPruneModel Context=Qwen-Image, P.(B)↓=14, M.(%)↓=79.4, L.(ms)↓=17862025.1176.66.49
TinyFusionModel Context=Qwen-Image, P.(B)↓=14, M.(%)↓=79.4, L.(ms)↓=17892025.1173.98.75
Base modelModel Context=FLUX.1-dev, P.(B)↓=12, M.(%)↓=100, L.(ms)↓=7152025.1166.50
FLUX.1 LiteModel Context=FLUX.1-dev, P.(B)↓=8, M.(%)↓=78.8, L.(ms)↓=5722025.1162.36.09
Base modelModel Context=FLUX.1 Lite, P.(B)↓=8, M.(%)↓=78.8, L.(ms)↓=5722025.1162.30
PPCL(8B)Model Context=FLUX.1-dev, P.(B)↓=8, M.(%)↓=74.4, L.(ms)↓=5352025.1160.54.03
Chroma1-HDModel Context=FLUX.1-dev, P.(B)↓=8.9, M.(%)↓=82.5, L.(ms)↓=17142025.1159.31.02
PPCL(6.5B)Model Context=FLUX.1 Lite, P.(B)↓=6.5, M.(%)↓=69.2, L.(ms)↓=4282025.1159.30.07
TinyFusionModel Context=FLUX.1-dev, P.(B)↓=8, M.(%)↓=74.4, L.(ms)↓=5342025.1151.113.8
HierarchicalPruneModel Context=FLUX.1-dev, P.(B)↓=8, M.(%)↓=74.4, L.(ms)↓=5432025.1150.313.38
Dense2MoEModel Context=FLUX.1-dev, P.(B)↓=12, M.(%)↓=100, L.(ms)↓=3122025.1140.321.52