OpenCodePapers

on-wise

Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeOverallCulturalTimeSpaceBiologyPhysicsChemistryModelNameReleaseDate
UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation✓ Link0.550.530.550.730.450.590.41UniWorld-V12025-06-03
Transfer between Modalities with MetaQueries0.550.560.550.620.490.630.41MetaQuery-XL2025-04-08
Emerging Properties in Unified Multimodal Pretraining✓ Link0.520.440.550.680.440.600.39BAGEL2025-05-20
Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation0.490.490.580.550.430.480.33playground-v2.52024-02-27
PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis✓ Link0.470.450.500.480.490.560.34PixArt-Alpha2023-09-30
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis✓ Link0.460.440.500.580.440.560.31SD3.5-large2024-03-05
SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis✓ Link0.430.430.480.470.440.450.27SDXL2023-07-04
Emu3: Next-Token Prediction is All You Need✓ Link0.390.340.450.480.410.450.27Emu32024-09-27
Show-o: One Single Transformer to Unify Multimodal Understanding and Generation✓ Link0.350.280.400.480.300.460.30Show-o2024-08-22
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling✓ Link0.350.300.370.490.360.420.26Janus-Pro-7B2025-01-29
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation✓ Link0.230.160.260.350.280.300.14Janus2024-10-17