OCR, Chat/Doc QA on AI2D (val)
84AI2D AccuracyQwen3-VL
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3-VLVision Encoder=Qwen3ViT, LLM=Qwen3-8B, Model Adaptation Type=Open Source2026.02 | 84 | |
| Qwen2.5-VLVision Encoder=Qwen2.5ViT, LLM=Qwen2-7B, Model Adaptation Type=Open Source2026.02 | 82.8 | |
| SigLIP2 | Qwen-3-8BVision Encoder=SigLIP2, LLM=Qwen-3-8B, Model Adaptation Type=Internal E-commerce Adaptation2026.02 | 82.6 | |
| SigLIP | Gemma3-4BVision Encoder=SigLIP, LLM=Gemma3-4B, Model Adaptation Type=Internal E-commerce Adaptation2026.02 | 80.7 | |
| SigLIP2 | Qwen-3-4BVision Encoder=SigLIP2, LLM=Qwen-3-4B, Model Adaptation Type=Internal E-commerce Adaptation2026.02 | 80.6 | |
| LLaVA-OVVision Encoder=SigLIP, LLM=Qwen2-7B, Model Adaptation Type=Open Source2026.02 | 80 | |
| SigLIP2 | e-Llama3.1-8BVision Encoder=SigLIP2, LLM=e-Llama3.1-8B, Model Adaptation Type=Internal E-commerce Adaptation2026.02 | 78.2 | |
| SigLIP2 | Lilium-8BVision Encoder=SigLIP2, LLM=Lilium-8B, Model Adaptation Type=Internal E-commerce Adaptation2026.02 | 76.9 | |
| Qwen2.5ViT | e-Llama3.1-8BVision Encoder=Qwen2.5ViT, LLM=e-Llama3.1-8B, Model Adaptation Type=Internal E-commerce Adaptation2026.02 | 76.6 | |
| SigLIP2 | Llama-3.1-8BVision Encoder=SigLIP2, LLM=Llama-3.1-8B, Model Adaptation Type=Internal E-commerce Adaptation2026.02 | 76.3 | |
| SigLIP2 | Lilium-4BVision Encoder=SigLIP2, LLM=Lilium-4B, Model Adaptation Type=Internal E-commerce Adaptation2026.02 | 74.8 | |
| Gemma3Vision Encoder=SigLIP, LLM=Gemma3-4B, Model Adaptation Type=Open Source2026.02 | 71.2 | |
| SigLIP2 | Lilium-1BVision Encoder=SigLIP2, LLM=Lilium-1B, Model Adaptation Type=Internal E-commerce Adaptation2026.02 | 63.9 |