Infographic Question Answering on InfoVQA (val)
70.5AccuracyLLaVA-OV-7B w/ CLI
Evaluation Results
| Method | Links | |
|---|---|---|
| LLaVA-OV-7B w/ CLIModel=LLaVA-OV-7B w/ CLI2026.01 | 70.5 | |
| LLaVA-OV-7BModel=LLaVA-OV-7B2026.01 | 69.5 | |
| InternVL-2-26BModel=InternVL-2-26B2026.01 | 68.9 | |
| IXC-2.5-7BModel=IXC-2.5-7B2026.01 | 68.1 | |
| LLaVA-OV-7B w/ SLIModel=LLaVA-OV-7B w/ SLI2026.01 | 67.6 | |
| InternVL-2-8BModel=InternVL-2-8B2026.01 | 66.5 | |
| LLaVA-OV-7B w/ DeepStackModel=LLaVA-OV-7B w/ DeepStack2026.01 | 62.2 | |
| LongVAResolution Strategy=UniRes2024.06 | 49.4 | |
| LLaVA-OV-0.5BModel=LLaVA-OV-0.5B2026.01 | 47.5 | |
| LLaVA-OV-0.5B w/ CLIModel=LLaVA-OV-0.5B w/ CLI2026.01 | 47.1 | |
| LLaVA-OV-0.5B w/ SLIModel=LLaVA-OV-0.5B w/ SLI2026.01 | 46.6 | |
| LongVAResolution Strategy=AnyRes2024.06 | 43.3 | |
| LLaVA-NeXT-Qwen22024.06 | 42 | |
| LLaVA-OV-0.5B w/ DeepStackModel=LLaVA-OV-0.5B w/ DeepStack2026.01 | 41 | |
| LLaVA-NeXT-LLaMA32024.06 | 37.6 | |
| LLaVA-1.6-Vicuna2024.06 | 37.1 | |
| VILA-13BModel=VILA-13B2026.01 | 10 |