Visual Reasoning on Open Images (test)
85.1AccuracyEVPG
Evaluation results
| Method | Links | |
|---|---|---|
| EVPGFramework=VisProg, Supervision Type=Supervised, Backbone=InternVL1.52025.12 | 85.1 | |
| EVPGFramework=VisProg, Supervision Type=Supervised, Backbone=BLIP_lavis2025.12 | 64.9 | |
| BLIP_lavisFramework=VisProg, Supervision Type=Zero-shot (baseline)2025.12 | 44.9 | |
| InternVL1.5Framework=VisProg, Supervision Type=Zero-shot (baseline)2025.12 | 40.6 | |
| BLIP_hgFramework=VisProg, Supervision Type=Zero-shot (baseline)2025.12 | 35.6 |