Visual Question Answering on InfographicVQA
83.14ANLSQwen2.5-VL-VIF
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-VL-VIFParams=7B, Base model=Qwen-2.5-VL2026.05 | 83.14 | |
| Qwen2.5-VLParams=7B, Base model=Qwen-2.5-VL2026.05 | 81.47 | |
| Qwen2.5-VL-SFTParams=7B, Base model=Qwen-2.5-VL2026.05 | 81.36 | |
| PaLI-3OCR pipeline input=true, Resolution=1064x10642023.10 | 62.4 | |
| TILTOCR pipeline input=true, Resolution=1064x10642023.10 | 61.2 | |
| PaLI-3OCR pipeline input=false, Resolution=1064x10642023.10 | 57.8 | |
| PaLI-XOCR pipeline input=false, Resolution=1064x10642023.10 | 49.2 | |
| DPModel Scale=Gemma 9B, Method=DP2026.04 | 45.9 | |
| Decoupled DiLoCoModel Scale=Gemma 9B, Method=DiLoCo2026.04 | 44.8 | |
| DPModel Scale=Gemma 5B, Method=DP2026.04 | 37.2 | |
| Decoupled DiLoCoModel Scale=Gemma 5B, Method=DiLoCo2026.04 | 36.2 | |
| LLaVA-1.5-VIFParams=13B, Base model=LLaVA-1.52026.05 | 32.71 | |
| LLaVA-1.5-SFTParams=13B, Base model=LLaVA-1.52026.05 | 31.73 | |
| LLaVA-1.5Params=13B, Base model=LLaVA-1.52026.05 | 30.35 | |
| LLaVA-1.5-VIFParams=7B, Base model=LLaVA-1.52026.05 | 29.95 | |
| LLaVA-1.5-SFTParams=7B, Base model=LLaVA-1.52026.05 | 28.58 | |
| LLaVA-1.5Params=7B, Base model=LLaVA-1.52026.05 | 28.17 | |
| DPModel Scale=Gemma 2B, Method=DP2026.04 | 25.8 | |
| Decoupled DiLoCoModel Scale=Gemma 2B, Method=DiLoCo2026.04 | 24.4 |