Question Answering on Unifybench++
71.2BLEURAP-MLLM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RAP-MLLMModel Size=13B, Method Category=Und. Only2026.05 | 71.2 | 72.3 | |
| Yo’LLaVAModel Size=13B, Method Category=Und. Only2026.05 | 61.4 | 59.4 | |
| GPT-4o+TPModel Size=200B, Method Category=Upper Bound, Input Prompt Type=Text Prompt2026.05 | 61.1 | 69.9 | |
| MC-LLaVAModel Size=13B, Method Category=Und. Only2026.05 | 60.6 | 58.3 | |
| Sync-R1Model Size=1.3B, Method Category=Unified Model2026.05 | 60.4 | 65.2 | |
| GPT-4o+IPModel Size=200B, Method Category=Upper Bound, Input Prompt Type=Image Prompt2026.05 | 59.4 | 65.8 | |
| Qwen2.5-VL + TPModel Size=3B, Method Category=Und. Only, Input Prompt Type=Text Prompt2026.05 | 57.9 | 77 | |
| UniCTokensModel Size=1.3B, Method Category=Unified Model2026.05 | 54.6 | 60.1 | |
| Yo’LLaVA(Phi-1.5)Model Size=1.3B, Method Category=Und. Only2026.05 | 51.1 | 49.8 | |
| Chamaleon+TPModel Size=7B, Method Category=Unified Model, Input Prompt Type=Text Prompt2026.05 | 50.9 | 56 | |
| Show-o+TPModel Size=1.3B, Method Category=Unified Model, Input Prompt Type=Text Prompt2026.05 | 50.7 | 57.9 | |
| Yo’ChameleonModel Size=7B, Method Category=Unified Model2026.05 | 50.6 | 58.2 | |
| Chameleon+IPModel Size=7B, Method Category=Unified Model, Input Prompt Type=Image Prompt2026.05 | 41.1 | 53.2 |