Knowledge-based Visual Question Answering on OKVQA (val)
66.7AccuracySMoLA-PaLI-X_FT (Specialist)
Evaluation Results
| Method | Links | |
|---|---|---|
| SMoLA-PaLI-X_FT (Specialist)Base model=PaLI-X, Per-task LoRA tuning=true, LoRA rank=42023.12 | 66.7 | |
| PaLM-ECategory=Specialist2023.12 | 66.1 | |
| PaLI-XCategory=Specialist2023.12 | 66.1 | |
| PaLI-XBase model=PaLI-X2023.12 | 66.1 | |
| SOTA [7]2023.12 | 66.1 | |
| CogVLMCategory=Specialist2023.12 | 64.7 | |
| SMOLA-PALI-XFTCategory=Generalist, Fine-tuned=true2023.12 | 62.4 | |
| PaLI-XFTCategory=Generalist, Fine-tuned=true2023.12 | 60.7 | |
| LLaVA-OV-7B w/ CLIModel=LLaVA-OV-7B w/ CLI2026.01 | 59.2 | |
| CogVLMCategory=Generalist2023.12 | 58.9 | |
| Qwen-VLCategory=Generalist2023.12 | 58.6 | |
| LLaVA-OV-7BModel=LLaVA-OV-7B2026.01 | 58.5 | |
| LLaVA-OV-7B w/ SLIModel=LLaVA-OV-7B w/ SLI2026.01 | 58.4 | |
| LLaVA-OV-7B w/ DeepStackModel=LLaVA-OV-7B w/ DeepStack2026.01 | 58.3 | |
| SMOLA48-PaLI-3FTCategory=Generalist, Fine-tuned=true2023.12 | 58.2 | |
| PaLI-3FTCategory=Generalist, Fine-tuned=true2023.12 | 56.2 | |
| Unified-IOCategory=Generalist2023.12 | 54 | |
| InternVL-2-8BModel=InternVL-2-8B2026.01 | 52.1 | |
| LLaVA-OV-0.5B w/ SLIModel=LLaVA-OV-0.5B w/ SLI2026.01 | 48.8 | |
| LLaVA-OV-0.5B w/ CLIModel=LLaVA-OV-0.5B w/ CLI2026.01 | 48.6 | |
| LLaVA-OV-0.5BModel=LLaVA-OV-0.5B2026.01 | 48.4 | |
| InternVL-2-26BModel=InternVL-2-26B2026.01 | 48.3 | |
| LLaVA-OV-0.5B w/ DeepStackModel=LLaVA-OV-0.5B w/ DeepStack2026.01 | 46.2 | |
| Flamingo-9Bshots=0-shot2023.09 | 44.7 | |
| IXC-2.5-7BModel=IXC-2.5-7B2026.01 | 29.2 | |
| SFT-CM3Leon-7Bshots=0-shot, SFT=true2023.09 | 23.8 | |
| VILA-13BModel=VILA-13B2026.01 | 1.6 |