Chart Understanding on AI2D
0.947AI2D ScoreClaude 3.5 Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude 3.5 SonnetOpen Data=false, Super-Image (SI)=false2025.12 | 0.947 | |
| Gemini-1.5 ProOpen Data=false, Super-Image (SI)=false2025.12 | 0.944 | |
| GPT-4oOpen Data=false, Super-Image (SI)=false2025.12 | 0.942 | |
| InternVL3LLM Backbone=Qwen2.5-7B, Open Data=false, Super-Image (SI)=false2025.12 | 0.852 | |
| MAmmoTH-VLLLM Backbone=Qwen2.5-7B, Open Data=true, Super-Image (SI)=false2025.12 | 0.84 | |
| Qwen2.5-VLLLM Backbone=Qwen2.5-7B, Open Data=false, Super-Image (SI)=false2025.12 | 0.839 | |
| MiMo-VL-RLLLM Backbone=MiMo-7B, Open Data=false, Super-Image (SI)=false2025.12 | 0.835 | |
| MAmmoTH-VLLLM Backbone=Qwen2.5-7B, Open Data=true, Super-Image (SI)=true2025.12 | 0.834 | |
| LLaVA-OVLLM Backbone=Qwen2-7B, Open Data=true, Super-Image (SI)=true2025.12 | 0.816 | |
| DeepSeek-VL2LLM Backbone=DeepSeek-MoE 27B, Open Data=false, Super-Image (SI)=false2025.12 | 0.814 | |
| LLaVA-OVLLM Backbone=Qwen2-7B, Open Data=true, Super-Image (SI)=false2025.12 | 0.814 | |
| Dream-VLLLM Backbone=Dream 7B, Open Data=true, Super-Image (SI)=false2025.12 | 0.812 | |
| Molmo-8B-DLLM Backbone=Qwen2 7B, Open Data=true, Super-Image (SI)=false2025.12 | 0.81 | |
| Dream-VLLLM Backbone=Dream 7B, Open Data=true, Super-Image (SI)=true2025.12 | 0.806 | |
| LLaDA-VLLM Backbone=LLaDA 8B, Open Data=true, Super-Image (SI)=false2025.12 | 0.778 | |
| DimpleLLM Backbone=Dream 7B, Open Data=true, Super-Image (SI)=false2025.12 | 0.744 | |
| Cambrian-1LLM Backbone=LLaMA3-8B, Open Data=true, Super-Image (SI)=false2025.12 | 0.73 | |
| LaViDa-DLLM Backbone=Dream 7B, Open Data=true, Super-Image (SI)=false2025.12 | 0.69 |