Visual World Modelling on AURORA-BENCH Average
7.36GPT-4o ScoreUNIWORLD-V1
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| UNIWORLD-V12026.02 | 7.36 | 33 | 86 | |
| OMNIGEN2026.02 | 6.59 | 30 | 89 | |
| BAGEL-14B2026.02 | 6.44 | 22 | 91 | |
| OMNIGEN22026.02 | 6.05 | 25 | 89 | |
| SWIRL (ITERATIVE)Method Strategy (SFT/Bootstrap/SWIRL)=SWIRL (ITERATIVE)2026.02 | 5.06 | 38 | 84 | |
| SWIRL (ITER. + SHARE)Method Strategy (SFT/Bootstrap/SWIRL)=SWIRL (ITER. + SHARE)2026.02 | 5 | 39 | 84 | |
| SWIRL (IDM → FWM)Method Strategy (SFT/Bootstrap/SWIRL)=SWIRL (IDM → FWM)2026.02 | 4.83 | 36 | 84 | |
| LIQUID-SFTTest-time Verification (N)=82026.02 | 4.77 | 29 | 85 | |
| LIQUID-SFTTest-time Verification (N)=42026.02 | 4.66 | 31 | 85 | |
| LIQUID-SFTTest-time Verification (N)=22026.02 | 4.53 | 31 | 85 | |
| LIQUID-SFTMethod Strategy (SFT/Bootstrap/SWIRL)=SFT2026.02 | 4.36 | 36 | 84 | |
| LIQUID-BOOTSTRAPMethod Strategy (SFT/Bootstrap/SWIRL)=Bootstrap2026.02 | 4.11 | 32 | 84 | |
| CHAMELEON-BOOTSTRAP2026.02 | 3.48 | — | — | |
| SMARTEDIT2026.02 | 3.41 | — | — | |
| CHAMELEON-SFT2026.02 | 3.26 | — | — | |
| BLIP3O-NEXT2026.02 | 3.14 | 49 | 72 | |
| GOT2026.02 | 3.14 | — | — | |
| InstructPix2Pix2026.02 | 1.43 | — | — |