Visual Question Answering on Unifybench++
78.4BLEUGPT-4o+TP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-4o+TPModel Size=200B, Method Category=Upper Bound, Input Prompt Type=Text Prompt2026.05 | 78.4 | 86.3 | |
| GPT-4o+IPModel Size=200B, Method Category=Upper Bound, Input Prompt Type=Image Prompt2026.05 | 75.1 | 78.4 | |
| RAP-MLLMModel Size=13B, Method Category=Und. Only2026.05 | 62.4 | 61.7 | |
| MC-LLaVAModel Size=13B, Method Category=Und. Only2026.05 | 62.3 | 63.6 | |
| Yo’LLaVAModel Size=13B, Method Category=Und. Only2026.05 | 61.6 | 62.5 | |
| Sync-R1Model Size=1.3B, Method Category=Unified Model2026.05 | 59.2 | 60.6 | |
| UniCTokensModel Size=1.3B, Method Category=Unified Model2026.05 | 50.5 | 52.1 | |
| Yo’LLaVA(Phi-1.5)Model Size=1.3B, Method Category=Und. Only2026.05 | 49.3 | 49.3 | |
| Yo’ChameleonModel Size=7B, Method Category=Unified Model2026.05 | 47 | 51.1 | |
| Show-o+TPModel Size=1.3B, Method Category=Unified Model, Input Prompt Type=Text Prompt2026.05 | 46.2 | 41.2 | |
| Chameleon+IPModel Size=7B, Method Category=Unified Model, Input Prompt Type=Image Prompt2026.05 | 44.6 | 49.7 | |
| Chamaleon+TPModel Size=7B, Method Category=Unified Model, Input Prompt Type=Text Prompt2026.05 | 41.1 | 48.9 | |
| Qwen2.5-VL + TPModel Size=3B, Method Category=Und. Only, Input Prompt Type=Text Prompt2026.05 | 40.4 | 72.6 |